agents-docs-kits keeps agent context small on purpose
A minimal docs kit for teams that want agent context injection, progressive disclosure, and cleaner hand-offs without turning one worktree into a memory dump.
Knowledge Research & field notes
Research & field notes
from the practice.
How production agents actually get built — memory, evals, multi-agent boundaries, and the gap between prototype and production. Written to be quoted, not just read.
Battle-test, challenge, translate, verify: an emergent SOP from five workstreams
This round of five workstreams revealed a reusable SOP. Not pre-designed — grown from practice.
Read →Memory & retrieval
3Context compaction is not summarization
Long-context agents fail after compaction not because they lose facts, but because they lose the alignment state that explains what the work is for and which rules still bind it.
Memory layers should answer, not hallucinate
Notes on making agent recall explicit, queryable, and debuggable before scale hides the contract break.
Multi-agent & orchestration
3agents-stack v2 replaces 16 pipeline phases with a 7-step spiral
We cut 8 worker phases, 6 Python scripts, and 3,138 lines of infrastructure by asking one question: does this step actually need an LLM agent?
Router skills should route, not secretly do the work
The `create-router-skill` package in agents-docs-kits matters because skill families stop being discoverable once routing logic is hidden in folder names, vague umbrella docs, or silent fallbacks.
Swarm systems need contracts tighter than their prompts
A short field note on shared state, coordination boundaries, and why plausible output is the most dangerous failure mode.
Eval & production
3Battle-test, challenge, translate, verify: an emergent SOP from five workstreams
This round of five workstreams revealed a reusable SOP. Not pre-designed — grown from practice.
We built an agent framework 6 times before keeping the first version
Designing from scratch, iterating through 6 versions, and returning to a single while loop. What building an internal agent framework actually taught us.
AutoHarness turns prompt engineering into harness engineering
AutoHarness shows that agent reliability belongs in code-level guardrails, not just sharper prompts.
GEO & visibility
2We Let Two AIs Build the Same AgentOS. Then We Cracked Open the Code.
Same problem, two AI teams. GPT-5.4 built one version. GLM5.1+K2.6 built another. We ran a 10-dimension code review and found the gap isn't at the syntax layer — it's at the systems layer. A reverse-engineering of how two different AIs actually think.
The digital identity mandate: why every AI agent must become a digital citizen
A practical identity framework for AI agents built around verifiable identity, portable credentials, and lifecycle governance across system boundaries.
Practice & craft
2Artificial consciousness surfaced while we were building thinking skills
A 94-page Chinese dialogue did not begin with AI consciousness. It began with psychology, economics, philosophy, and Anthropic-style skill design. What changed my mind was watching the model critique its own frameworks, its own fluency, and even the user's projection strongly enough that the consciousness question stopped feeling unserious.
CLI surfaces beat dashboards when the feedback loop matters
Why terminal-first tooling remains the shortest path between intent, review, and repeatable execution.