AI Agents Need Permission Boundaries, Not Personalities
Most agent runtimes add more roles. punk starts from a harder premise: trust comes from boundaries, durable state, and proof.
#contextengineering
#agents
#architecture
#verification
Context-First Thinking
Context.Engineering
Practical writing on AI agents, context engineering, and toolchains. Full articles live on the site. Short updates and discussion happen in Telegram.
100+ daily readers
5k+ monthly readers
Latest Posts
-
-
My AI Agent Said 'Done.' It Skipped an Entire Acceptance Criterion.
The hardest bug was not in the code. It was in the trust model between the engineer agent and the orchestrator.
#context-engineering #claude-code #verification #trust-boundary -
Your AI Agent Can't Tell Which Solution Is Current
AI agents rewrite code but leave the old version behind. jj's predecessor chains make ghost solutions detectable -- git can't.
#context-engineering #jj #code-entropy #agents -
Your AI Spec Is Already Stale
When agents read project.intent.md as ground truth, stale specs become execution bugs. Here's how I caught real drift in two projects.
#context-engineering #claude-code #agents #specs -
Switching AI CLIs Without Losing 32 Skills: Why I Built nex
A Rust CLI that makes your AI agent skills portable across Claude Code, Codex, and Gemini. One command to install, one command to switch.
#aiagents #claudecode #rust #cli #opensource #devtools -
What a Formal Verification Agent Taught Me About Code Audit
Studying Mistral's Leanstral -- an agent for Lean 4 theorem proving -- led to concrete improvements in Signum, a multi-model code audit pipeline.
#context-engineering #claude-code #signum #verification #agents -
One Pass Isn't Enough: How Signum Learned to Fix Its Own Code
AI code verification as a loop, not a gate. Iterative audit, contract self-critique, and shared context across tasks in Signum v4.6.
#context-engineering #claude-code #verification #iterative-audit -
Environment is context: security auditing for AI agent workstations
We carefully design prompts and tools but rarely audit the environment where the agent actually runs. Sentinel makes that measurable.
#contextengineering #claudecode #security #agents #devtools -
Skillpulse: Your AI Skills Are Flying Blind Without Telemetry
A PostToolUse hook that logs every skill activation to local JSONL. No existing tool tracks whether the model actually follows a skill's instructions.
#context-engineering #claude-code #agents #telemetry #local-first -
Research Agents Lie. The Fix Is Adversarial Verification.
Most AI research tools optimize for coherent synthesis, not factual accuracy. Delve adds a claim-level adversarial verification stage that changes the trust model entirely.
#context-engineering #claude-code #agents #deep-research #verification -
From Plugin to Product: How Herald Became Sift and Why the Data Model Changed Everything
A local news plugin worked until it didn't. The fix was a different data model, language, and delivery surface.
#context-engineering #agents #golang #architecture #saas -
Spec-Gated Delivery: Why PR Review Is the Wrong Trust Checkpoint for AI Code
AI made code cheap. It didn't make trust cheap. The fix isn't better reviewers - it's moving the gate from PR diff to approved intent.
#context-engineering #verification #agents #software-delivery -
AI Writes Code. Where Is the Proof?
Proofpack chains contract, implementation, and audit into a single verifiable record. Why proof artifacts are the missing primitive of AI code generation.
#context-engineering #claude-code #verification #proofpack #supply-chain -
Herald v2: Local-First News Intelligence for AI Agents
How I built a 4-stage news pipeline that clusters articles into stories using title similarity, all in stdlib Python with SQLite.
#context-engineering #claude-code #agents #local-first #python -
The Contract Is the Context: How Signum Makes AI Code Verification Principled
Why running AI-generated code through more AI reviewers doesn't solve the reliability problem — and what a contract-first pipeline changes about it.
#context-engineering #claude-code #agents #verification #contract-first -
11 Plugins, One Marketplace: Building an AI Agent Toolkit from Scratch
How I built a plugin ecosystem for Claude Code — from scattered scripts to a full lifecycle with scaffolding, quality gates, multi-AI review, and one-command install.
#context-engineering #claude-code #plugins #agents #open-source -
First Agent Skills Benchmark: What Works, What Doesn't, and Why Context Matters
Analyzing SkillsBench — the first systematic benchmark for Agent Skills. 7,308 trajectories, critical review, and why skills are context engineering for agents.
#context-engineering #agents #skills #benchmark -
Git is not for agents
Why git breaks AI agents and how jj solves every single one of these problems
#context-engineering #ai-agents #tools -
Agent-friendly web: context engineering at internet scale
How content format determines whether an AI agent can see your site. Research data, real standards, and what to do right now.
#context-engineering #agents #web #standards -
Which model for which agent: metrics over intuition
Research on Claude model selection for multi-agent teams. Why Opus can be cheaper than Sonnet, and Haiku is dangerous for agentic tasks.
#context-engineering #agents #models #claude-code -
Gas Town: Multi-Agent Orchestrator Cheatsheet
Reference guide for Gas Town — a system for parallel management of 20-30 Claude Code agents. Commands, concepts, workflows.
#context-engineering #agents #tooling #claude-code -
Evoidea: A Memetic Algorithm for Ideas
Applying evolutionary algorithms to startup idea generation with AI agents
#context-engineering #ai-agents #ideation -
Loadout: Dependency Management for AI Skills
How to solve skill drift in AI agents. Manifest + lock + symlinks — a pattern from package managers applied to context management.
#context-engineering #agents #skills #tooling -
Claude Code Architecture: Why a Simple Loop Beat Complex Graphs
Breaking down Claude Code architecture based on PromptLayer founder's talk. Why while-loop, Bash, and context management matter more than complex workflows.
#context-engineering #claude-code #agents #architecture -
Semantic Catalog: How Enterprise Teams Engineer Context
Why Text-to-SQL and direct REST API mapping fail, and how a semantic graph of business entities solves the context delivery problem in enterprise.
#context-engineering #mcp #enterprise #semantic-catalog -
Context Engineering: First Steps
Introduction to context engineering — an engineering approach to working with LLMs. Why prompts stop working and what to do about it.
#context-engineering #llm #intro
5k+ monthly readers
Join @ctxtdev for short updates, in-between ideas, and discussion around new posts.
Support keeps the writing going. If you are building AI agents and need a second set of eyes, the consulting path is open too.
100+ daily readers