Hub
Software Factories & AI-Assisted Engineering
More working software. Proof in every release.
A coding agent that writes a patch is not a delivery system. These articles cover intake-to-release pipelines, review gates, CI patterns and the metrics that predict release risk when agents join the factory.
Evidence before autonomy. Each article below is written for operators and builders who need eval angles, decision framing and practices they can run — not another generic tip list.
Related on the main site: Software factories
Articles
- Review Gates for AI-Written Code2026-11-13
Three review gates ask three different questions, and each approval only counts for one stage, one commit and one exact packet.
- Specs With Two Reviewers for AI Agents2026-11-13
A spec an agent can be held to has numbered criteria, a way to verify each, negative cases that point back at them, and two independent reviews tied to the exact text.
Posts on this topic
- Gemini 4 Hydrogen arrives with Orchestrator handoffs in Antigravity · Models, Tooling & Developer Practice · Software Factories & AI-Assisted Engineering
Google released a fast coding model and a mode that passes work between a planning model and Hydrogen inside one session, backed by Google-reported benchmark claims.
- AlphaProof Code proves libsignal security properties in machine code · AI Reliability & Operations · Software Factories & AI-Assisted Engineering
Google DeepMind used a multi-agent Lean framework to formally verify the Signal protocol's reference implementation at the AArch64 machine-code level.
- Claude Haiku 5.5: a fast model for subagents and high-volume work · Models, Tooling & Developer Practice · Customer Experience Agents
Claude Haiku 5.5: 1M context, 128K output, $0.10/$0.50 per million tokens up to 100K-token prompts. Where it fits in routing, caching and subagent work.
- Claude Code trims background-subagent status overhead by about 99% · Software Factories & AI-Assisted Engineering · Models, Tooling & Developer Practice
Claude Code's background-subagent status line now comes from Haiku 5.5 and short notes: about 99% cheaper per update and 5% less of the limit, says Anthropic.
- Mistral Studio Managed Agents: durable harness with approval gates · Workflow Automation · Software Factories & AI-Assisted Engineering
Mistral Studio Managed Agents (public preview): one Python agent definition, three run modes, crash-resume, approval gates and default tracing. What to test.
- Muse Spark Open: Meta releases open weights for an 816B multimodal model · Models, Tooling & Developer Practice · Software Factories & AI-Assisted Engineering
Muse Spark Open: Meta's 816B/42B-active multimodal open-weights model. License conditions, the 700GB-plus hardware floor and a self-hosting checklist.
- Nemotron 3.5 Super VL: open multimodal agents from data center to desktop · Models, Tooling & Developer Practice · AI Products & Copilots
Nemotron 3.5 Super VL: NVIDIA's open 120B/12B-active vision-language MoE with 1M context, NVFP4 weights, a permissive license and Bolt edge models.