AI Agents
19 essays tagged with AI Agents.
AI Agents as Insider Risks: What Nadella's Trust Architecture Requires
A research-backed analysis of Satya Nadella's AI insider-risk argument: external authorization, reasoning transparency, agent-to-agent provenance, independent evidence, and the limits of emergency stops.
Muse for Small Business: The Approval Is Part of the Product
A deeper assessment of Meta's September 29 Muse expansion: connector scope, meaningful approvals, cross-app recovery, and the economics of owner attention.
Mistral Vibe: Editable Memory and the Difference Between an App and a Snapshot
A research assessment of Mistral's September Vibe updates: Agentic Knowledge Base, spreadsheets, Mini App Canvas, migration, and artifact verification.
OpenAI After DevDay: Cheaper Intelligence, Persistent Agents, and the Cost of Accepted Work
A research assessment of GPT-6.1 Sol, Dots, and the DevDay platform changes: what the evidence supports, where costs move, and how to evaluate persistent work.
Grok 4.7 and Team Bots: Shared Expertise Needs Explicit Authority
A research assessment of Grok 4.7 and Team Bots: model–harness specialization, shared credentials, private memory, and evidence for team productivity.
Harness Engineering on September 26, 2026: From Agent Loops to Personal-Agent Operating Systems
A current practitioner field report on harness engineering through September 26, 2026: Meta Muse, JAZ’s minimalist harness, event-sourced coding agents, agentic-commerce access disputes, embodied agents, and the next research questions.
Muse Spark, Muse Code, and Glimmer: Meta’s Full Agent Stack
A practitioner map of Meta’s 2026 agent stack: Muse Spark 1.3, Muse Code’s event-sourced multi-agent harness, Glimmer’s local open weights, Model API, voice, avatars, connectors, and AI-glasses distribution.
Harness Engineering: The September 2026 Practitioner’s Field Guide
A primary-source review through September 15, 2026: controlled harness comparisons, evolving safety defenses, context inheritance, managed runtimes, implementation availability, and the next experiments.
Harness Engineering in September 2026: Measurement, Evolution, and Operational Reality
A critical research map of harness engineering through September 10, 2026: new benchmarks, automatic optimization, reusable tools, long-running agents, public implementations, and unresolved questions.
Self-Improving Harnesses: HarnessDev, HoH, and the Promotion Boundary
A practitioner analysis of HarnessDev, Harness-of-Harness, HarnessOpt-Bench, and HarnessCompass, with concrete boundaries for evaluation, durable state, recovery, and harness promotion.
The Harness Engineering Roadmap for 2026–27: From Agent Loops to Proof-Carrying Runtimes
A source-grounded 18-month roadmap for harness engineering across release manifests, portable trajectories, lifecycle security, skill evaluation, delegated authority, recovery, economics, and governed adaptation.
Skill Lift: How to Gate Agent Skills With Paired Live Evals
An implementation guide to evaluating agent skills as executable release artifacts using paired baselines, Skill Lift, ATIF trajectories, security checks, domain graders, and CI gates.
HarnessRisk in Practice: Turn the Agent Lifecycle Into a Security Test Matrix
A deep implementation guide to lifecycle security testing for agent harnesses: configuration, extensions, runtime, persistence, actions, recovery, evidence oracles, and release gates.
Harness Engineering in August 2026: The Control Plane Gets Measured
A source-backed state of the field on harness engineering: what shipped, what the newest research measured, what practitioners are debating, and the roadmap from agent loops to proof-carrying runtimes.
DeepSeek Harness: Everything Is a Plugin—Except Trust
A source-code critique of DeepSeek Harness and Cordis: why an everything-is-a-plugin runtime matters, where reversibility stops, and why self-evolution still needs an immutable control plane.
Your Agent Followed the Rule—or Did It? Harness-IF and A2E Change Agent Evaluation
A deep implementation guide to rule-level, surface-aware, trajectory-based agent evaluation using the new Harness-IF and A2E research.
Harness Engineering: The Runtime Became the Product
A source-backed 10-day field report on Harness-IF, A2E, Thea, Microsoft Copilot Studio, and Claude Code—and what their combined evidence changes for agent engineering.
From Claude Code to Cowork and Claude Tag: Anthropic's Agent Product Stack
How Claude evolved from chat to coding, cross-app work, and a persistent team agent—and what identity, memory, permissions, and oversight each surface requires.
The Autonomy Budget: How Enterprises Should Decide What AI Agents Are Allowed to Do
A practical governance model for granting AI agents bounded authority based on risk, evidence, policy confidence, evals, and approval.