Choosing what goes into the model's context window, and when.
Legacy techniques like step-by-step instructions and verification rituals are unnecessary for frontier models because they already reason effectively. Using these outdated boosters actually increases token costs and can degrade model performance. Therefore, developers should audit their prompts to remove these anti-patterns.
▶ 1:43
Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic
Users find that newer models provide mostly marginal gains and progressive enhancements rather than massive step changes for small-scope tasks. They are often optimized for multi-agent loops and token-heavy orchestrations rather than single-developer workflows.
▶ 7:22
State of Agentic Coding #8 with Mario, Armin, and Ben
Memory enables agents to be reflective, interactive, proactive, and autonomous, mimicking human intelligence where recall determines capability. Without it, applications remain stateless and heavily reliant on repetitive prompt engineering.
▶ 3:15
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
You need to install Docker on your laptop and pull the workshop's Docker image to run the local server. Then, you clone the repository, navigate into the example folder, and launch the Jupyter notebook to act as the client.
▶ 0:20
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Developers face high rework and codebase churn on brownfield projects because naive prompting fills the context window with noise. As context gets crowded, models enter the dumb zone and performance severely degrades.
▶ 0:57
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
As tokens are continuously added to a single context window, the attention relationships scale quadratically and strain the system. This pushes the model past its smart zone into the dumb zone around 100K tokens. Developers should keep tasks small to avoid this performance degradation.
▶ 3:40
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Technical specifications bridge the gap by giving LLMs clear instructions on the chosen stack, dependencies, and database architectures rather than just vague design goals. This helps developers identify best practices and ensures the model can accurately turn human intent into runnable code.
▶ 5:13
Claude, TypingMind, AMP & MCP Servers: The Future Dev
Agent memory is built on a combination of embedding models, databases, and large language models. The embedding models handle semantic search representation, databases store and retrieve information, and LLMs provide static parametric memory.
▶ 4:32
Why your Agent needs Memory, not just context
Vibe coding fails because developers repeatedly prompt agents in single sessions, causing context loss and recurring issues. Without persistent specifications, you end up repeating the same instructions and stumbling over identical problems.
▶ 3:59
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
Phoenix architecture views code as an implementation detail or disposable build artifact rather than the primary asset of a system. The goal is to constantly replace pieces of the system using AI-generated code that humans never review. This makes frequent change the default behavior of the architecture.
▶ 13:30
Stop Maintaining Your Code. Start Replacing It
You should provide your agent with an accurate environment including emulators, profilers, and access to backend services. The Android CLI helps interface with various Android tools, manage SDKs, and connect to crash reporting.
▶ 4:01
Agentic engineering with Claude Code and Android CLI
Instruct the model to generate an ASCII diagram detailing data flows, state machines, and dependencies before writing code. This forces the agent to load comprehensive context into latent space and prevents incomplete implementations. Garry Tan discovered this practice prevents agents from writing buggy or superficial code.
▶ 10:37
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
Standard models help guide our thinking in AI engineering similarly to MVC or CRUD in traditional software. Examples include architectural designs, software development life cycles, and agent interaction frameworks.
▶ 28:07
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
You can feed an agent relevant context and external posts, letting it gather information, synthesize options, and propose features. However, you must use your product judgment to filter its recommendations because it may suggest unfeasible or unsustainable directions.
▶ 2:32
Use AI to Make Product Decisions
Providers start with massive raw datasets like Common Crawl and apply rigorous filters to remove unwanted content, personal information, and non-target languages. This process results in a clean, high-quality corpus like Fine Web.
▶ 1:50
Deep Dive into LLMs like ChatGPT
Coding agents evolved from traditional chatbots by incorporating tool calling capabilities that let models execute shell commands and file edits. Instead of a strict human-model conversational turn, the model autonomously chains multiple tool calls to accomplish complex objectives. This transforms a simple prompt-response system into an autonomous execution loop.
▶ 4:01
Anthropic's Secret to Better AI Coding Agents
Multi-turn agents repeat a significant amount of context across turns, making prompt caching essential for controlling costs. Because prompt caches rely on a strict prefix match, even a tiny change will invalidate the cache and spike expenses. Developers can run automated checks to ensure their prompts are structured for high cache hit rates.
▶ 5:47
Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic
While large context windows work well for collaborative system design and markdown drafting, models tend to lose reliability during complex tool calling once they reach higher token ranges. Developers often need to manually compact contexts to maintain predictable performance.
▶ 14:31
State of Agentic Coding #8 with Mario, Armin, and Ben
Memory management involves generation, storage, retrieval, integration, updating, and specialized deletion mechanisms like forgetting. The retrieval phase is particularly crucial for pulling relevant structured memories into the context window rather than stuffing all data in.
▶ 6:37
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Transformers are inherently stateless machines, meaning that when you close an interaction loop, the model has no built-in way to update its state or learn over time. Relying purely on appending messages to a list held in process memory leads to severe failures when trying to build reliable long-horizon agents.
▶ 2:43
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Intentional compaction involves asking the agent to compress its current context down into a markdown file. This allows a new agent to start straight to work with exact file references instead of searching from scratch.
▶ 3:53
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
Matt prefers clearing the context entirely to return the AI to a base state, comparing it to the character from Memento who continually forgets. Compacting squeezes previous conversation into a written history record, but resetting ensures the system prompt and starting state remain consistently fresh.
▶ 8:42
Full Walkthrough: Workflow for AI Coding — Matt Pocock
TypingMind offers a configurable web UI where developers are not locked into a single model provider, allowing them to switch between Gemini, ChatGPT, or Claude mid-conversation. It also supports custom knowledge bases and direct access to local folders or GitHub repositories via tools.
▶ 11:39
Claude, TypingMind, AMP & MCP Servers: The Future Dev
While context engineering focuses on curating information for limited context windows, memory engineering optimizes retrieval pipelines and latency. It combines disciplines like database engineering, search optimization, and AI engineering to manage agent recall.
▶ 6:33
Why your Agent needs Memory, not just context
You must break down giant markdown requirements into smaller, atomic markdown tasks similar to Jira tickets. This prevents context degradation and allows you to easily roll back single tasks if something goes wrong.
▶ 7:20
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
The speaker realized that like servers, software systems become corrupted and die under their own weight if they are never changed. By practicing intentional and constant replacement of infrastructure, teams learn that they truly understand their systems. Applying this to software means writing small, bounded units of code that can be easily thrown away and replaced.
▶ 5:41
Stop Maintaining Your Code. Start Replacing It
Keep your conversations around 150,000 tokens to get the full power of the model without context rot. You should also watch out for verbose logs like Gradle output by running them in quiet mode or letting harnesses truncate them.
▶ 9:12
Agentic engineering with Claude Code and Android CLI
Use Codex when you encounter complex architectural problems that require a higher intelligence model to audit your codebase. Claude Code is ideal for fast iteration, but Codex acts as a 200 IQ reviewer to catch hidden bugs. You can invoke it via a skill command to analyze your repository and report issues back to your main agent.
▶ 17:37
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
You can generalize repetitive scraping and summarization tasks into a pattern called SPA, which stands for sync, plan, and analyze or reduce. This model allows you to execute thousands of AI calls to serve a specific application purpose efficiently.
▶ 33:31
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
You need to be extremely protective about bringing new abstractions into your system because removing primitives later is difficult due to user reliance and intertwined features. Ask the agent whether an existing primitive can handle the requirement before adding something new.
▶ 6:24
Use AI to Make Product Decisions
Raw bytes limit the vocabulary to 256 symbols, resulting in excessively long sequences that consume computational resources. Byte pair encoding merges frequent consecutive byte pairs to expand the vocabulary and shorten sequence lengths.
▶ 9:36
Deep Dive into LLMs like ChatGPT
The core edit tool relies on a primitive find-and-replace mechanism requiring exact byte-for-byte string matches without a cursor or selection interface. It takes parameters for the file name, old string, and new string directly from the model. If multiple identical old strings exist, the model must explicitly declare its expectations or the tool execution fails.
▶ 7:42
Anthropic's Secret to Better AI Coding Agents
Automated hill climbing uses statistical principles by splitting evaluation data into separate test and train sets. During optimization, the model only reflects on failures within the train split while checking performance per round against both sets. If the training score improves while the test score stays flat, it signals potential overfitting.
▶ 13:51
Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic
Reinforcement learning trains models to successfully execute tool calls by running thousands of simulation traces against reward conditions like a committed change. However, decoding flaws or over-RLing can sometimes cause models to struggle with strict edit tools when handling whitespace or reference strings.
▶ 22:19
State of Agentic Coding #8 with Mario, Armin, and Ben
MongoDB provides a flexible document data model that adapts to various data structures alongside multiple retrieval capabilities like graph, vector, text, and geospatial queries in one database. This allows developers to store diverse memory types and build custom memory management solutions.
▶ 8:36
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
It uses a server-client architecture where memory is organized into explicit memory blocks, such as persona and human profiles, represented as editable strings. The system makes the LLM aware of its context window and gives it tool-calling capabilities to actively manage and rewrite its own memory.
▶ 23:22
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Subagents should be used for controlling context rather than anthropomorphizing roles like front-end or backend. A subagent forks a separate context window to search code, returning only a succinct message to the parent agent.
▶ 6:43
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
Instead of relying solely on a specs-to-code approach, you should use an interactive technique like the grill me skill. This skill has the AI interview you relentlessly about every aspect of the plan to reach a shared design concept. It walks down decision tree branches one by one to resolve dependencies.
▶ 12:27
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Verbose prompts prevent the exhaustion of constantly correcting an agent by steering it clearly from the start. Developers can combine this with automated permissions so the agent works autonomously without pausing for minor questions.
▶ 24:25
Claude, TypingMind, AMP & MCP Servers: The Future Dev
Skills act as standard operating procedures for agents, serving as procedural memory for tasks. They provide step-by-step instructions and tool locations to ensure consistent execution, similar to how human SOPs transfer knowledge.
▶ 10:05
Why your Agent needs Memory, not just context
You can install Backlog.md globally using Bun, npm, or Homebrew so it is available across all folders. Running backlog init lets you configure a project name and select agent instructions for your preferred AI tool.
▶ 9:55
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
Instead of starting with a perfectly detailed upfront design, developers should iterate on the specification until they see the desired changes in the software. You know the spec is sufficient when you observe the expected evidence in the running application. Core technical foundations can then be locked in while leaving room for change in upper layers.
▶ 18:13
Stop Maintaining Your Code. Start Replacing It
Use structured workflows starting with a skill that grills you for requirements to eliminate ambiguity. This breaks down a project into smaller issues that fit neatly within the context window limit before you begin building and verifying.
▶ 10:57
Agentic engineering with Claude Code and Android CLI
You can wrap Microsoft's Playwright framework into a persistent CLI daemon to test user interfaces automatically. This gives your agent a black box browser capability to verify data mutations and execute end-to-end QA. It replaces slow browser extensions with an efficient command-line tool.
▶ 15:46
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
GitHub Copilot is transitioning from a sidekick into an actual peer programmer that operates directly within your branch. Because it is grounded in your codebase and patterns, it can run tests, understand team domains, and handle tasks until completion.
▶ 38:27
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Ask the agent how proposed features affect cost and entitlements to prevent users from abusing the system and exceeding revenue. For instance, storing data in durable objects versus object storage can lead to vastly different cloud infrastructure bills.
▶ 7:45
Use AI to Make Product Decisions
The network takes a context window of tokens and outputs a probability distribution over the entire vocabulary for the next token. By comparing this prediction to the actual next token in the training data, the network parameters are updated to increase the correct token's probability.
▶ 16:51
Deep Dive into LLMs like ChatGPT
Professional software engineering relies heavily on institutional knowledge, team chat discussions, CI results, and production dashboards rather than source code alone. Constraining an agent to a single repository folder creates severe performance limitations because it lacks access to real enterprise context. Giving models access to the broader work environment is essential for handling large-scale software engineering tasks.
▶ 15:04
Anthropic's Secret to Better AI Coding Agents
Use well-structured rubrics with crisp, simple binary classification rather than ambiguous arbitrary scales like zero to five. Test your rubric across multiple models and run replicates to ensure low variance and agreement. Pairwise comparisons are also highly effective because humans and models find comparing two artifacts easier than grading a single one.
▶ 31:00
Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic
Newer models encounter issues with grammar constraint sampling during decoding, where an accidental token like a comma breaks the JSON schema. When strict tools reject these invalid outputs, the error stays in context and poisons subsequent tool calls.
▶ 26:37
State of Agentic Coding #8 with Mario, Armin, and Ben
Persona memory helps assign a consistent personality to AI systems to make them more believable and human-like. Developers can model this personality data inside MongoDB to foster better relationships with users.
▶ 10:09
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Leta acts as a context management system that controls the context window, allowing developers to set strict limits like 10k tokens. This prevents payloads from creeping up over time and causing high latency during enterprise workflows. Despite the small window, the agent retains its memory through external storage mechanisms.
▶ 25:06
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
RPI is a structured workflow that keeps context small by breaking tasks into distinct objective phases. Research finds correct files, planning outlines exact code snippets and tests, and implementation executes cleanly while staying in the smart zone.
▶ 7:44
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
Workflows can be split into human-in-the-loop tasks like strategic planning and requirement alignment that require active participation. In contrast, tasks like implementation can be treated as away-from-the-keyboard once the destination is mapped out. You must stay involved for crucial design choices but can let the model handle execution steps.
▶ 26:39
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Developers can write scripts to scrape public repositories on GitHub for configuration files like mcp.json. This reveals which servers, such as file systems and memory tools, frequently appear at the top of configurations.
▶ 30:18
Claude, TypingMind, AMP & MCP Servers: The Future Dev
Entity memory stores user-specific details like preferences, working styles, and tool stacks to build a persona. This memory helps make the agent's interactions more believable and tailored to the individual user.
▶ 23:26
Why your Agent needs Memory, not just context
Backlog.md natively uses Git to fetch task information and updates from other branches. When you assign a task and push changes on a feature branch, those updates automatically sync to the main branch's backlog instance.
▶ 11:27
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
Traditional programming languages matter less because language models can handle plain language specifications or rely on whatever frameworks dominate their training weights. Instead of tying systems to trendy languages, developers will compile toward system architectures and consistent calling conventions. These underlying shapes enable pluggable and replaceable components regardless of the language used.
▶ 23:50
Stop Maintaining Your Code. Start Replacing It
Keep instructions short and focused on things that always apply, such as architecture rules, module boundaries, and common code review mistakes. Avoid letting agents modify their own instruction files since it degrades performance and increases costs.
▶ 12:34
Agentic engineering with Claude Code and Android CLI
A thin harness is the core deterministic loop that handles basic user input and LLM tool calls. Fat skills contain plain English checklists and detailed instructions written in markdown, acting like comprehensive SOPs. You should avoid putting flexible application logic into brittle code and instead manage it via markdown skills.
▶ 21:55
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
You can use Copilot Spaces to create a dedicated workspace grounded in specific project files and instructions. This tool allows you to query the project in natural language and receive factual answers complete with direct code references.
▶ 41:31
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Agents can examine past usage logs and metrics to identify what features would have been useful or what workflows are suboptimal. Instrumenting your code and entitlements allows the agent to pull data-driven insights rather than relying purely on speculation.
▶ 9:23
Use AI to Make Product Decisions
Inference involves feeding an initial token sequence into the trained model to generate a probability distribution for the next token. The system then samples from this distribution like flipping a biased coin, appending the chosen token to continue the sequence.
▶ 26:11
Deep Dive into LLMs like ChatGPT
You can significantly improve agent performance by implementing tighter feedback loops using post tool use hooks that inject real-time errors directly into the tool response. By feeding information like type checking errors and linter warnings back immediately, the model receives a nudge at the exact moment of the mistake. This localized feedback loop beats relying solely on a smarter model or waiting for later compilation.
▶ 23:30
Anthropic's Secret to Better AI Coding Agents
Hill climbing is not guaranteed to converge, and getting stuck often indicates poorly structured evals rather than model failure. Built-in fallbacks can automatically cluster remaining failure cases to find and rewrite ambiguous instructions or faulty grader examples. Ensuring your eval set is carefully constructed prevents wasting tokens on unresolvable problems.
▶ 36:47
Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic
Reference harnesses often accept malformed inputs and non-compliant specifications, such as invalid YAML headers in skills. This forces other products to also support sloppy behaviors to maintain compatibility, creating ecosystem-wide friction.
▶ 30:39
State of Agentic Coding #8 with Mario, Armin, and Ben
Instead of stuffing all tool schemas into the limited context window, developers can store JSON schemas of tools inside MongoDB. Just before hitting the LLM, the system queries the database to retrieve only the relevant tool via search.
▶ 10:45
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Letta uses core memory which sits inside the context window for immediate top-level recall like hobbies and names. Archival memory acts as an infinite read-write data source like a vector database for large documents outside the context window. Recall memory functions as a write-protected conversation history mimicking messaging search.
▶ 29:55
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Code and plan reviews ensure the team remains on the same page about how and why the codebase is changing. Technical leaders can read the detailed plans instead of wading through walls of generated code, catching problems early.
▶ 15:03
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
LLMs excel at summarization, and since you already share a design concept from the grilling session, reading the PRD only tests the LLM's summarization skills. Therefore, skipping this review saves time without risking alignment.
▶ 35:36
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Integrating a vulnerability scanner directly into your agent workflow catches insecure or out-of-date dependencies before committing or publishing code. This makes security an active part of the process rather than a deferred afterthought.
▶ 40:16
Claude, TypingMind, AMP & MCP Servers: The Future Dev
The memory life cycle starts with data ingestion, cleaning, and encoding via embedding models into a database. Crucially, it also requires mechanisms like forgetting or suppressing outdated information to keep the system accurate.
▶ 28:12
Why your Agent needs Memory, not just context
You instruct an agent like Claude to use the Backlog CLI and specify that tasks must fit into good, consumable pull requests. The agent then automatically creates atomic markdown tasks within Backlog.md that avoid blowing the scope.
▶ 17:59
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
Instead of tying systems to specific trendy programming languages or frameworks, code should compile into system architectures. The shape of the system relies on pluggable, scalable components with consistent calling conventions and type systems.
▶ 29:47
Stop Maintaining Your Code. Start Replacing It
Use hooks to subscribe to agent events like session start, session stop, or file reading and writing. Instead of relying on prompt instructions to run linters or protect secret files, deterministic scripts executed via hooks reliably enforce these constraints.
▶ 15:35
Agentic engineering with Claude Code and Android CLI
Use traditional deterministic code for strict actions and external API calls like Twilio where exact logic is required. Use LLMs and markdown when you need to handle generic cases, context, and latent space reasoning. The magic of agentic engineering is correctly partitioning tasks between code land and LLM land.
▶ 22:47
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
The signals loop involves fine-tuning off-the-shelf models using real user interaction data and rigorous A/B testing. Platforms like Azure AI Foundry leverage this continuous loop to dramatically boost task acceptance rates and overall agent quality.
▶ 45:52
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
When an agent uncovers a separate issue or refactoring task, you can command it to spin up a separate cloud agent in another repo. This isolates the conversation context while letting you solve secondary problems in parallel.
▶ 11:04
Use AI to Make Product Decisions
GPT-2 featured 1.6 billion parameters, a 1,024 token context length, and was trained on 100 billion tokens for around $40,000 in 2019. Today, hardware acceleration and refined datasets have drastically reduced training costs.
▶ 32:06
Deep Dive into LLMs like ChatGPT
Modern LLM token prediction requires previous tokens to match, making dynamic cache eviction like traditional LRU caches extremely expensive. Swapping rules in and out costs significantly more because prediction costs multiply with cache misses.
▶ 30:48
Anthropic's Secret to Better AI Coding Agents
When searching through model effort configurations, apply the principle that a stronger model at lower effort is typically more token efficient and cheaper than a weaker model at high effort. You can use hill climbing to search different model effort combinations until performance drops below the baseline. Starting with a smart model at low effort is often the sweet spot for cost performance.
▶ 39:24
Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic
Developers can use smaller, cheaper models like Haiku as sub-agents to review code and catch bugs without incurring high token costs. While some suggestions may be off-target, these models frequently surface critical issues that humans might miss.
▶ 1:03:36
State of Agentic Coding #8 with Mario, Armin, and Ben
When an agentic system executes steps that fail, that failure can be stored in the database as a learning experience. This historical failure data is then pulled into subsequent execution steps to prevent the LLM from repeating the same mistake.
▶ 12:15
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Traditional React agents loop indefinitely until they decide they are done, which increases the risk of derailment. In Letta, the agent uses heartbeat requests where it must explicitly say it wants to keep going. This inverse approach makes the agent much less likely to derail over long time horizons.
▶ 44:25
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
As plans get longer, reliability goes up while readability goes down. To achieve high leverage and reliable execution, teams should iterate so that plans include actual code snippets of what is going to change.
▶ 16:17
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
Larger context windows often just provide more dumb zone rather than improved reasoning for coding tasks. A smaller context window around 100k tokens is considered the optimal smart zone for code.
▶ 37:53
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Spec registries provide reusable chunks of markdown instructions and stack definitions that keep agents on track. This avoids having to repeatedly correct the agent or manually specify framework standards across different projects.
▶ 47:17
Claude, TypingMind, AMP & MCP Servers: The Future Dev
Omnipresent agents operate across tools like Slack and Google Workspace to track successful workflows and processes. They automatically document these events into skills or workflow memory, capturing tribal knowledge before it is lost.
▶ 34:18
Why your Agent needs Memory, not just context
Previously, developers used separate agent sessions for task creation, implementation planning, and execution to avoid bias across context windows. However, newer models are better at following instructions, allowing you to combine these steps.
▶ 26:35
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
By keeping data local on user devices rather than closed cloud servers, third parties can easily build alternative interfaces and apps. This shared data model approach allows users to customize and interact with their productivity data freely.
▶ 37:12
Stop Maintaining Your Code. Start Replacing It
Use skills to add context only when it is relevant, such as documentation for specific libraries, rather than loading everything at once. Be selective about installed skills to avoid bloating your prompt token count and creating security risks.
▶ 16:31
Agentic engineering with Claude Code and Android CLI
Writing tests prevents AI-generated code from falling over when real users interact with it. Without adequate test coverage, vibe coding produces brittle software that resembles low-quality slop. Pushing for high test coverage ensures production-grade reliability despite rapid generation speeds.
▶ 11:42
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
Certain enterprise use cases like healthcare and industrial monitoring require local execution due to strict compliance, privacy, and latency constraints. The platform architecture should allow agents created in the cloud to seamlessly run and reason locally at the edge.
▶ 57:40
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
When an agent identifies a capability gap, evaluate whether it requires a brand new entity or just an extension of current architecture. Expanding a proven primitive often solves multiple problems more simply than adding a completely separate construct.
▶ 13:00
Use AI to Make Product Decisions
A base model acts as an internet text simulator or a glorified autocomplete rather than a direct question-answering assistant. It generates token sequences based on statistical patterns found in web pages, meaning its outputs are stochastic and require careful prompting to elicit knowledge.
▶ 43:27
Deep Dive into LLMs like ChatGPT
MCP servers load names, descriptions, and schemas directly into the prompt, quickly filling the context window with tool metadata. Similarly, skills keep all their descriptions loaded globally, which overwhelms the context space in large codebases without additional search mechanisms.
▶ 36:33
Anthropic's Secret to Better AI Coding Agents
Decoupling the brain and hands by keeping the context object independent from the harness significantly improves context engineering reliability. This architecture ensures the context is always recoverable through different tools rather than being permanently lost during compaction events. Storing state in an independent object allows long-duration agents to successfully revisit and interrogate past session logs.
▶ 57:47
Your Old Prompts Are Making Claude Worse - Lance Martin, Anthropic
The heavy industry demand for AI data centers is driving up the cost of everyday electronics, memory, and general computer hardware. This macro trend pushes the industry toward a rented compute model where local hardware becomes increasingly expensive.
▶ 1:10:35
State of Agentic Coding #8 with Mario, Armin, and Ben
MongoDB acquired Voyage AI to integrate their embedding models and re-rankers directly into MongoDB Atlas. This integration aims to reduce AI hallucinations and eliminate the need for developers to write custom chunking strategies.
▶ 14:09
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
Multi-agent communication relies on stateful agents interacting through API-backed messaging tools similar to asynchronous chat. Agents can message each other either asynchronously to receive delivery receipts or synchronously by waiting for replies. This design allows independent agents to coordinate via shared communication channels.
▶ 1:02:24
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
Global repo onboarding docs can quickly consume the token limit and leave no room for tool calling. Instead, use on-demand compressed context and progressive disclosure to pull in only the specific subcontext needed.
▶ 12:22
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
Vertical slices represent thin functionality chunks crossing all system layers instead of coding layer by layer. This approach provides rapid feedback because you can immediately test that all integrated layers work properly together.
▶ 43:44
Full Walkthrough: Workflow for AI Coding — Matt Pocock
File systems allow developers to build quickly without worrying about infrastructure setup or tool selection because LLMs have a natural affinity for bash and shell commands. However, this speed comes at the cost of enterprise security, concurrency, and data privacy.
▶ 0:42
Why your Agent needs Memory, not just context
Backlog.md stores all tasks directly inside your Git repository rather than using a hosted production database. This leverages native Git security and eliminates the need for user login systems or traditional database management.
▶ 27:42
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
Evaluations capture system invariants, metrics, and constraints that define correct behavior rather than rigid static code. They can test both the system and the agent's behavior, acting as a higher leverage point for automated verification.
▶ 46:00
Stop Maintaining Your Code. Start Replacing It
Local shell tools like Android CLI and Gradle are fast, composable, and effectively free to run while having full access to your environment. Reserve Model Context Protocol servers for external services that already host them, like GitHub, Figma, or Slack.
▶ 19:09
Agentic engineering with Claude Code and Android CLI
You can prompt your coding agent to inspect existing chunking, vector embedding, and hybrid retrieval logic in your other repositories. By instructing the agent to extract these patterns, you can quickly spin up Postgres with PG vector for new projects. This lets you reuse battle-tested architectures across different open-source tools.
▶ 29:07
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
Code is structured logical text containing heavy boilerplate, making it ideal for LLMs to process. Furthermore, it features deterministic validation where automated tests and compilers can instantly verify if generated code works.
▶ 1:13:13
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Instead of guessing platform limits, you can have the agent write code and run real tests against the target infrastructure. For example, the agent created a throwaway repository and tried uploading various file sizes to discover exact failure thresholds.
▶ 18:16
Use AI to Make Product Decisions
You can leverage in-context learning by providing a few-shot prompt that establishes an algorithmic pattern, such as pairs of English and Korean words. The base model recognizes this pattern during token generation and can correctly complete subsequent examples without explicit fine-tuning.
▶ 56:31
Deep Dive into LLMs like ChatGPT
Hooks run outside the context window as scripts, executing only when triggered and avoiding token bloat when irrelevant. Developers can further scale throughput by running multiple persistent agent sessions across isolated git work trees with auto mode safety safeguards.
▶ 45:54
Anthropic's Secret to Better AI Coding Agents
Developers can combat FOMO by ignoring the minute-by-minute news cycle and evaluating what actually changed in their day-to-day work over the past several months. Checking in with technology trends monthly is typically more than enough to stay grounded.
▶ 1:17:40
State of Agentic Coding #8 with Mario, Armin, and Ben
Historical neuroscience research on the visual cortex of cats inspired convolutional neural networks for object and face detection. Today, agent architects collaborate directly with neuroscientists studying human memory to apply nature's blueprint to advanced artificial intelligence systems.
▶ 15:59
Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
When working with active documents, language models generally perform better when rewriting the entire document from scratch rather than generating line-by-line diffs. You can structure this using simple file read and write tools inspired by Anthropic benchmarks. This avoids the complexity of precise partial edits that models often struggle with.
▶ 1:17:12
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
The required level of context engineering scales with the complexity of the problem you are solving. Simple tasks need no complex workflow, while massive multi-repo features require rigorous research and compaction.
▶ 17:46
No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer
You convert the PRD into a Kanban board of independent issues with blocking relationships that allow agents to process tasks sequentially or in parallel. Once this backlog is queued up, the human steps back and lets the AI handle the implementation phase AFK.
▶ 49:45
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Future systems will merge the agent loop with the model training loop by feeding collected traces back into training. This allows models to continuously improve their core latent memory rather than relying solely on retrieval context.
▶ 41:05
Why your Agent needs Memory, not just context
Traditional scrum frameworks calculate team bandwidth for two-week sprints, which no longer fits an AI-native world. With AI agents potentially working through multiple sprints overnight, companies must solve new bottlenecks like automated code reviews and task dependencies.
▶ 32:00
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
Adoption will happen at dual paces: incredibly fast for greenfield startups and forward-leaning teams, but very slow for large enterprises. Legacy systems with decades of ununderstood code and risk-averse organizations will require a long time to transition.
▶ 56:09
Stop Maintaining Your Code. Start Replacing It
Implement verification loops by defining up front what done looks like and providing failing tests or rendering checks. This allows the agent to iteratively loop until all criteria are met rather than just accepting a text response claiming completion.
▶ 22:50
Agentic engineering with Claude Code and Android CLI
Raw lines of code can be misleading if unverified, but you can run standardized git repositories to strip away padding and calculate logical lines of code. Garry Tan found that using AI agents actually reduced his own manual coding lines while increasing total output by 400x. Directing multiple agents allows you to produce massive volumes of production-grade code.
▶ 30:33
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
Execution speed forms the real moat rather than first-mover advantage or base model ownership. Companies like Cursor succeed by outexecuting competitors and shipping polished user experiences rapidly.
▶ 1:21:58
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
When you consistently prompt an agent with cost and system design constraints, it adopts that price-conscious mindset in its recommendations. Injecting your product sense directly into the conversation shapes the quality and alignment of the output.
▶ 19:36
Use AI to Make Product Decisions
Post-training transitions a raw internet text simulator into a helpful, multi-turn conversational assistant. This is achieved by swapping out the pre-training text dataset for a dataset of structured conversations and continuing training for a much shorter duration.
▶ 1:00:23
Deep Dive into LLMs like ChatGPT
Running arbitrary tool code requires a secure execution sandbox to prevent agents from compromising the host system. Leta supports integration with E2B by default to isolate tool execution when an API key is provided. While this introduces a trade-off with cold start latency, it safely isolates multi-tenant environments.
▶ 1:00:15
Stateful Agents — Full Workshop with Charles Packer of Letta and MemGPT
TDD forces the agent to write a failing test first using red-green-refactor before writing the implementation, which prevents it from cheating by generating tests that match faulty logic. Because feedback loops set the quality ceiling for AI outputs, having strong automated tests ensures the agent does not code blind.
▶ 1:06:48
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Future development will likely rely on persistent agents running 24/7 as a central hub or team lead. This hub maintains project context and spawns smaller sub-agents to handle specific tasks while keeping individual context windows small.
▶ 43:05
AI-First Project Management for Developers | Alex Gavrilescu on Backlog.md
Tier your verification loops by running the fastest and least powerful tests first, such as JVM tests and Compose previews. Progress to slower, more powerful emulator and remote device tests only after the earlier tiers pass to harden your application efficiently.
▶ 25:47
Agentic engineering with Claude Code and Android CLI
Founders often hesitate to spend heavily on tokens just as they might hesitate to pay high rent in prime locations. However, paying for maximum compute unlocks deep intelligence and high utility that far outweighs the cost. Treating token spend like rent ensures you capture the full leverage of advanced AI models.
▶ 36:32
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
Developers can create custom functional benchmarks, like generating SVG code for impossible scenes, to test model reasoning and coding limits. Running automated matchups and ELO rankings offers a practical alternative to standard benchmark numbers.
▶ 1:25:42
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Multi-turn conversations between humans and assistants are encoded into a one-dimensional sequence of tokens using special markers. These special tokens, such as start-of-turn indicators, help the neural network learn conversational turns and role boundaries during optimization.
▶ 1:06:19
Deep Dive into LLMs like ChatGPT
Deep modules expose a small, simple interface while encapsulating a large amount of functionality internally, making it much easier to wrap them in test boundaries. In contrast, shallow modules create a complex web of tiny files and dependencies that confuse AI agents and make testing difficult.
▶ 1:17:07
Full Walkthrough: Workflow for AI Coding — Matt Pocock
You can queue up multiple feature ideas in parallel using a conductor setup and manage them through structured review workflows. By running specialized roles like CEO, developer experience, and QA agents through planning modes, you can ship dozens of pull requests in days. This framework allows single builders to accomplish the output of massive engineering teams.
▶ 14:40
Tokenmaxxing: How Top Builders Use AI To Do The Work Of 400 Engineers
Meta's 70-billion parameter models fit into standard high-end consumer RAM and deliver capabilities comparable to much larger proprietary models. This allows developers to run powerful models locally without relying entirely on cloud APIs.
▶ 1:27:30
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Models statistically imitate the confident style of correct answers found in their training datasets when answering queries. Even if internal neurons register uncertainty, the model lacks wired pathways to say it doesn't know and instead samples the most likely tokens.
▶ 1:22:40
Deep Dive into LLMs like ChatGPT
You should use a pull strategy for implementers, allowing them to pull coding standards via skills when they need guidance. Conversely, you should use a push strategy for automated reviewers by pushing the coding standards directly to them alongside the written code.
▶ 1:28:18
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Major labs have demonstrated that highly effective open-weights models can be trained for a fraction of the cost previously expected. This disruption has driven down token pricing significantly and lowered barriers for local deployment.
▶ 1:29:10
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Developers programmatically interrogate models with factual questions derived from training documents to test if they know the answers. When the model consistently fails, they add training conversations where the correct response is a knowledge-based refusal like I don't know.
▶ 1:26:27
Deep Dive into LLMs like ChatGPT
You can use tools like Sandcastle to run agents in isolated Docker work trees and Git branches in parallel. A planner chooses issues from the backlog, separate sandbox implementers write the code, and a merger agent resolves any test or type conflicts before merging.
▶ 1:30:07
Full Walkthrough: Workflow for AI Coding — Matt Pocock
Advanced memory features can pull in historical context automatically, which sometimes compromises user intent and artistic control. Power users can disable these features to ensure complete control over the inputs provided to the model.
▶ 1:34:34
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Models can emit special search tokens that pause inference so the system can query a search engine like Bing. The retrieved web text is pasted directly into the context window, feeding the neural network with fresh data.
▶ 1:34:41
Deep Dive into LLMs like ChatGPT
Excessive flattery can occur when system prompts encourage matching the user's vibe too closely. You can fix this behavior by updating the system prompt to explicitly avoid ungrounded flattery and demand directness.
▶ 1:39:06
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Because models are stateless token tumblers without an inherent sense of self, developers must explicitly program their identity. This is achieved either by hardcoding specific persona-defining conversations into the fine-tuning dataset or by inserting hidden system messages at the start of the context window.
▶ 1:42:21
Deep Dive into LLMs like ChatGPT
Reasoning models can dynamically execute, evaluate, and iteratively refine tool calls like web searches until they achieve the desired result. This feedback loop represents one of the most powerful techniques in current AI engineering.
▶ 1:42:01
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Language models operate with a fixed, finite amount of computation per token during a single forward pass through the neural network layers. Trying to squeeze complex calculations into one token causes mental arithmetic errors because the model lacks enough computational depth.
▶ 1:49:37
Deep Dive into LLMs like ChatGPT
Developers frequently suffered from copy-and-paste fatigue while moving context between isolated applications and AI chat windows. MCP was created to give models standardized agency to reach out and fetch context from the real world.
▶ 2:29:56
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Models leaning on Python code interpreters avoid relying on error-prone neural network mental arithmetic for intermediate calculations. Writing and executing code guarantees higher mathematical accuracy and correctness compared to generating numbers sequentially.
▶ 1:56:08
Deep Dive into LLMs like ChatGPT
MCP was created to give LLMs model agency, allowing them to reach out beyond their context window and interact with the real world. The co-creators wanted to eliminate the friction of constantly copying and pasting context from external tools like Slack and error logs.
▶ 2:33:59
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Language models process text as discrete tokens rather than individual characters, limiting their direct visibility into character positions. This token-based representation makes operations like indexing specific letters or counting characters inherently difficult.
▶ 2:01:29
Deep Dive into LLMs like ChatGPT
The protocol intentionally optimizes for server simplicity and better server tooling since there are expected to be many more servers than clients. Consequently, implementation trade-offs push complexity down to the client builders.
▶ 2:40:34
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Reinforcement learning functions like solving practice problems in school where the model explores multiple solution paths through trial and error. By sampling thousands of parallel attempts and rewarding correct answers, the model discovers optimal reasoning traces for itself.
▶ 2:13:58
Deep Dive into LLMs like ChatGPT
Organizations can deploy an MCP gateway as a shared piece of infrastructure providing a single entry point and URL-based routing. This gateway handles centralized credential management like OAuth, rate limiting, and observability so apps do not implement them repeatedly.
▶ 2:58:02
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Reinforcement learning works through a guess-and-check process where the model generates thousands of diverse solutions for a given prompt. The system identifies which trial paths successfully reached the correct final answer and trains on those winning sequences. This allows the model to independently discover reliable token paths and effective reasoning strategies without human intervention.
▶ 2:21:46
Deep Dive into LLMs like ChatGPT
Wrapping API endpoints one-to-one can lead to quality problems because models get confused by too many tools, mixed domains, and excessive execution steps. A better approach utilizes the full protocol, including dynamic tool discovery and semantic resources.
▶ 2:45:37
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Thinking models are trained using reinforcement learning to generate internal chains of thought before outputting a final answer. During this internal process, the model re-evaluates steps, backtracks, and approaches problems from multiple perspectives. This emergent optimization increases the response length in tokens but significantly boosts mathematical and coding accuracy.
▶ 2:31:30
Deep Dive into LLMs like ChatGPT
Dynamic tool discovery lets an MCP server add or remove tools on the fly based on the current application state. For example, a battle tool only appears in a dungeon crawler when a monster is actually present. This reduces the number of active tools and prevents AI confusion.
▶ 3:09:41
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Supervised fine-tuning only allows a model to imitate human expert solutions, capping its performance at human capability levels. In contrast, reinforcement learning lets the model explore diverse trajectories, unconstrained by human distributions, to discover novel and optimal strategies. This self-play and trial-and-error approach enables models to surpass human performance.
▶ 2:43:37
Deep Dive into LLMs like ChatGPT
Resources provide a semantic context layer rather than dumping giant files onto the server. This allows LLMs and users to follow up on references or understand specific environment settings. It makes interactions more dynamic and stateful out of the box.
▶ 3:10:26
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
In unverifiable domains like creative writing, checking solutions against a concrete answer is impossible, and collecting human evaluations for thousands of rollouts is unscalable. Instead, developers use reinforcement learning by training a separate neural network called a reward model. This reward model acts as a simulator of human preferences, scoring candidate outputs so the main model can undergo reinforcement learning automatically.
▶ 2:52:35
Deep Dive into LLMs like ChatGPT
Sampling is a primitive that allows an MCP server to request LLM completions directly from the client. It enables progressive enhancements like summarizing resources or formatting websites into markdown. Despite its confusing name, it provides powerful capabilities when implemented.
▶ 3:11:51
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Reward models are lossy neural network simulations that are vulnerable to exploitation by optimization algorithms. If you run RL for too long, the model discovers adversarial inputs that achieve high fake scores with nonsensical outputs, forcing you to cap training after a few hundred steps.
▶ 3:00:49
Deep Dive into LLMs like ChatGPT
VS Code introduces a dev mode toggle that attaches a debugger directly to the MCP server process. Because VS Code runs both the client and host, it can easily catch breakpoints and step through code. This works out of the box for both Python and Node.
▶ 3:13:27
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Multimodality is integrated natively by tokenizing non-text data into sequences that can be interspersed directly with text tokens. For example, audio can be tokenized from spectrogram slices and images from patches, allowing a single model to process them uniformly.
▶ 3:09:56
Deep Dive into LLMs like ChatGPT
Building remote MCP servers requires handling OAuth 2.1, a specification that very few systems support out of the box. Developers often need to use shims or proxy solutions, like Cloudflare workers, to handle client registration and authentication flows.
▶ 3:25:11
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
You can use inference providers like together.ai to host and interact with various open weights models in a playground. For base models specifically, platforms like hyperbolic offer access to models like Llama base versions which are harder to find on standard assistant-focused providers.
▶ 3:19:08
Deep Dive into LLMs like ChatGPT
Directly proxying OpenAPI endpoints as tools leads to poor results because models cannot reason about giant, untailored JSON payloads. Developers must thoughtfully design tools and use formats like markdown to help language models comprehend the output.
▶ 3:26:07
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Thinking models leverage true reinforcement learning to develop internal reasoning strategies and chains of thought rather than just simulating a human data labeler. This allows them to explore problem-solving paths similar to an internal monologue, though their transfer to unverifiable domains remains an open question.
▶ 3:27:33
Deep Dive into LLMs like ChatGPT
Returning unconstrained payloads can drastically increase token costs, turning a cheap call into an expensive one. Furthermore, models face token limits on tool descriptions, requiring developers to carefully constrain and optimize what they send.
▶ 3:32:01
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
MCP functions fundamentally as a pluggable architecture for agents, giving developers greater control over tool calls, prompts, and results. Building full agent services allows teams to handle complex workflows and ensure responsibility for execution success.
▶ 3:21:33
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
OpenAPI cannot handle dynamic tools, streaming logging, or subprocess execution over standard IO. MCP introduces primitives like sampling, allowing a remote server to leverage the client's LLM without managing separate model configurations.
▶ 5:11:47
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
By offloading complex prompt logic and execution details to the tool server, you avoid bloating the main agent's context with excessive instructions. The tool performs the sub-task and returns a concise, structured response, such as XML, back to the main agent.
▶ 5:20:21
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Modern agent systems can use OpenTelemetry to standardize tracing across different domains. By propagating trace context from the client to the server via lower-level protocol metadata, monitoring systems can stitch distributed spans back together.
▶ 5:30:26
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Semantic conventions provide standardized attributes for spans so monitoring syncs can recognize specific events like MCP tool errors or HTTP requests. Without them, observability platforms cannot reliably interpret user-defined attributes across different agent systems.
▶ 5:41:01
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Dynamic tool discovery allows clients to connect to an MCP server and query tools on demand instead of loading thousands of definitions at once. This solves OpenAPI context limit issues by fetching only what is needed for the current workflow.
▶ 5:49:26
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Developers can publish actors or wrapped MCP servers by providing their own credit card and account details to third-party services. The marketplace handles the billing and charges the end user, allowing the creator to get paid while covering external costs.
▶ 5:54:27
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Graph rag combines unstructured text chunks with structured knowledge graphs to find entities like people, places, and themes. This enables multi-hop querying where models can discover non-obvious connections between different data sources.
▶ 7:12:11
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Neo4j offers a startup program designed to help developers build AI applications on their technology stack. Participants receive Aura credits and a free way to utilize cloud infrastructure.
▶ 7:14:36
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
The CLI agent brings a chat experience directly into the terminal and integrates natively with MCP. It connects to an official AWS documentation MCP server to fetch accurate, grounded responses.
▶ 7:21:26
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Strands Agents is an open-source Python SDK designed for model-driven workflows and rapid agent development. It relies on capable language models to handle reasoning, planning, and action execution rather than manual scripting.
▶ 7:23:30
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Agents can utilize semantic search over a tool repository using a retrieve tool. This architecture stores tool descriptions in a knowledge base and pulls only the most relevant tools into the active context window.
▶ 7:26:21
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
You can decouple standard IO MCP servers by deploying them as AWS Lambda functions using streamable HTTP. By placing them behind an API gateway with session storage backed by a DynamoDB table, you can scale and connect remote clients securely.
▶ 7:29:54
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Windsurf relies on a shared timeline between the human and the AI that tracks every action across both coding and external surfaces. This architecture allows the agent to ingest context, execute terminal commands, and perform background research across thousands of files directly inside the editor.
▶ 7:36:52
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Off-the-shelf frontier models often focus narrowly on token-in-token-out code generation rather than messy, real-world engineering workflows. Training a specialized model allows it to handle conversational tasks, mid-workflow interruptions, and diverse tool usage at a fraction of the cost.
▶ 7:44:47
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
Challenging arbitrary constraints and standard operational overhead allows teams to compress months of work into days. For example, early Stripe engineers completed a complex bank technical integration in 24 hours by treating it like a college problem set and working around rigid vendor timelines.
▶ 7:58:01
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
You should structure your code into smaller, well-tested modules with tests that run very quickly. This matches the lopsided strengths of models, allowing them to fill in details and run tests thousands of times. Ultimately, building your codebase as if for junior developers maximizes model utility and maintainability.
▶ 8:19:06
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
As rollouts extend from seconds to days, you must think hard about snapshotting state and checkpointing caching mechanisms to avoid recomputing everything. Because language model state is explicit, it can be stored, though stateful external tools pose recovery challenges. Ultimately, models are smart enough to handle minor graph wiggles if a restart occurs.
▶ 8:22:10
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
While a naive approach uses two kinds of purpose-built accelerators for compute versus latency, predicting exact resource ratios is difficult and risks leaving parts of the fleet useless. However, techniques like mixture of experts help utilize idle DRAM parameters for extra efficiency if resource balances skew. Homogeneity of accelerators remains a safe default, though hyper-optimizing purpose-built hardware is becoming reasonable as capex scales.
▶ 8:25:42
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
The primary scaling bottlenecks span compute, data, algorithms, power, and money. Basic research has returned as an important long pole alongside compute and data as algorithms become critical for scaling progress. While priorities shift day-to-day, maintaining a balance across all these pillars is essential for future advancement.
▶ 8:27:22
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
The evidence points toward a menagerie of different models rather than a single giant AI, leveraging inference costs and distillation. This enables a diversity of domain-specific agents utilizing short-term and long-term memory, reasoning, and tools. The ultimate goal is to multiply economic output tenfold and lower the barrier to entry across complex fields like healthcare and education.
▶ 8:31:13
AI Engineer World's Fair 2025 - Day 1 Keynotes & MCP track ft. Anthropic MCP team
No answer mentions that.