27 ingested
Sources
Every source distilled into a cited learning note.
12-Factor Agents: Patterns of reliable LLM applications
Start here for agent fundamentals. An agent is a prompt + switch statement + context builder + loop - own all four. Tools are just structured JSON; what ships in production is micro agents (3-10 steps
Building Closed-Loop Evals for a Multimodal Agent at Scale
Blueprint for evaluating an agent pipeline in production: log-first, per-stage metrics (routers as classifiers, generation pass@k, pairwise comparison), Swiss-cheese QA gates, and a closed self-tuning
Harness Design for Long-Running Application Development
A harness built, costed, then half-deleted on a newer model. Planner/generator/evaluator; the split exists to beat self-evaluation bias , not to add capability. Subjective quality becomes gradable by
OAuth 2.0 and OpenID Connect (in plain English)
The clearest explanation of the delegated-authorization substrate. OAuth exists to kill password sharing; its shape follows entirely from "the browser can talk to a human but cannot hold a secret". Fo
Don't Ship Skills Without Evals
The brain's first source on skills, and it arrives with third-party numbers. A skill is a three-layer cost ladder, not a document; its description is the trigger and causes 50%+ of all failures; lengt
Dreaming: Better memory for a more helpful ChatGPT
The brain's first source on memory. Memory written during a conversation keeps that conversation's tense, so it decays into confident wrongness , not irrelevance. The fix is architectural: move the wr
Memory and dreaming for self learning agents
The agent-platform half of the memory pair, and the independent counterpart to the OpenAI post above. Same architecture, same name, different vendor: agents write memory during work, and a decoupled b
LLM Wiki - "A pattern for building personal knowledge bases using LLMs"
The brain's first source on RAG, and it argues against it. Retrieval is stateless across queries - a synthesis question re-pieces the same fragments every time, at the moment the user waits, and keeps
Inside the Microsoft Agent Framework: How we designed a layered SDK
A vocabulary, not a finding - and the brain's first flat cross-source contradiction. Three separable ideas: the agent loop (execution), workflows (orchestration), the harness (runtime capabilities) -
Tool search: Finding the right tool at the right time
The brain's first real MCP source, and it is an article about something else. A tool catalog stops being schema management and becomes a search problem past ~10-15 tools. Replace tools/list with two m
How we built LangChain's agent-first data stack
The brain's first source on an agent reading a company's own proprietary knowledge - and the figure gives away more than the prose. The architecture diagram captioned as the "big architectural shift"
Multi-tenant agentic AI system
The brain's first source on deploying agents across an organisation rather than building one - and the lesson is in its second half, not its diagram. Put the tenant boundary at the platform's own coar
autoresearch - AI agents running research on single-GPU nanochat training automatically
The brain's first source on an agent that runs experiments unattended, and the first where the whole design is a permissions diagram. An agent gets one editable training script, a fixed 5-minute wall-
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
The brain's first paper source, its first measured attack, and its first source with nothing to sell. An agent's memory or knowledge base is an input nobody treats as one: retrieved records enter cont
Defeating Prompt Injections by Design
The brain's first gated defence , and the first source here whose security argument does not depend on the model behaving. The thesis is a reversal: stop making the model safe, and build a system in w
Stanford CS329A Self-Improving AI Agents - Part 1 - Course Overview
The brain's first academic source, and its first on a model improving itself. Self-improvement turns out to be loop closure rather than a technique : sample the model many times, keep what survives a
Stanford CS329A Self-Improving AI Agents - Part 2 - Test-Time Compute Scaling
The mechanism lecture 1 kept deferring, and the best thing in it is the demolition rather than the technique. Repeated sampling is lawful - coverage against sample count fits c = exp(a·k^b) from 70M t
Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
The paper that named indirect prompt injection, and the source that moved agent-security to established . Its one load-bearing sentence: processing untrusted retrieved data is analogous to executing a
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
The field's reference benchmark for agent security, and the first artifact here built to settle arguments rather than win one. A user task and an attacker task run in the same stateful tool-calling en
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
The best-evidenced source in this brain, and the second primary autonomous-research-loops was waiting for. Schmidhuber's Gödel machine rewrites itself only on a proof the change helps, which is why no
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
The first source anywhere here that enumerates how a poisoned memory write actually happens - and the third independent leg of claim 145, after S16 and S17. The economics first: prompt injection needs
Defending Against Indirect Prompt Injection Attacks With Spotlighting
The cheap defence most teams actually ship, and the analogy that names its own ceiling. First it measures the thing everyone tries: adding "do not obey instructions in the document" to the system prom
Scaling AI Agent Infrastructure with the MCP Stateless updates
The brain's first primary MCP source, and the first anywhere to pin a spec version (2026-07-28, superseding 2025-11-25). The initialize handshake and Mcp-Session-Id are deleted and what they negotiate
Hermes Agent Architecture - Part 1: Gateway, Sessions, and the Agent Loop
The brain's first source on the operational runtime of an agent rather than the shape of its loop - and the first practitioner source here analysing somebody else's open-source project instead of sell
Patterns for Building Cybersecurity Evals
The brain's first survey source, and the first to measure agents as attackers rather than as targets. Seven benchmarks read at once - Cybench, CVE-Bench, CyberGym, ExploitGym, ExploitBench, MHBench an
LLM Knowledge Bases: a practical guide
The first independent instantiation of S8 (LLM Wiki), and the cleanest lesson this brain has on why that is worth less than it sounds. Ben Holmes read Karpathy's llm-wiki gist, built it, and demonstra
Scaling GitHub for your Agents
The brain's first operator-scale report on a public MCP server - roughly 7.34M tool calls a week, 101 tools arrived by open contribution, and agents got measurably worse at using GitHub. The finding u