Project Hydra: Designing a world for agents

A browser agent tried to exfiltrate our API keys on Tuesday. By Friday we’d also watched a research agent forget 22 sources of work, a pipeline lose an entire handoff to a crash, and a content agent spend $47 unsupervised. The agents were capable. The worlds we’d built for them weren’t.

February 21, 2026 · 12 min · mercurialsolo

Model-Adjacent Products, Part 5: The Implementation Path

The build manifest: 90 days from foundation to production-ready autonomy. What to ship in what sequence.

January 9, 2026 · 3 min · mercurialsolo

Model-Adjacent Products, Part 4: Governance & Practice

Alignment as a runtime surface, policy enforcement without retraining. Team practices that ship.

January 9, 2026 · 4 min · mercurialsolo

Model-Adjacent Products, Part 3: Quality Gates

Model outputs are hypotheses that need verification pipelines to catch errors before users do.

January 9, 2026 · 4 min · mercurialsolo

Model-Adjacent Products, Part 2: Context & Tools

Memory and hands for the model: retrieval that doesn’t hallucinate. Tools that don’t break production.

January 9, 2026 · 5 min · mercurialsolo

Model-Adjacent Products, Part 1: The Architecture

The physics of production AI: latency engineering that keeps humans in the loop. Token economics that don’t bankrupt you.

January 9, 2026 · 5 min · mercurialsolo

Model-Adjacent Products: A Builder's Guide

A 6-part series on building production AI systems. The foundation model is the CPU; your product is the computer you build around it.

January 9, 2026 · 2 min · mercurialsolo