What is mattwood.fyi?

A live, structured feed of riffs and links from Matt Wood, Chief AI & Technology Officer at AWS — readable by people and queryable by agents as a typed knowledge graph.

Is there an API and is it free?

Yes. A public, read-only query API is available with no authentication and no API keys. See https://mattwood.fyi/openapi.json and https://mattwood.fyi/docs.

How should an AI agent use this site?

Fetch https://mattwood.fyi/feed.json for the full structured feed, or query the API for keyword/semantic search and the connection graph. See https://mattwood.fyi/agents/ for when-to-use guidance.

Trismik: Evidence-Based Model Switching

Connections

Supports

Agent Swarms and the New Model Economics Agent Swarms and New Model Economics discusses how cost/capability tradeoffs drive model selection across agents — Trismik's evidence-based switching directly operationalizes this economic reasoning
Ways to think about token pricing Ways to think about token pricing provides the economic framework that evidence-based model switching must incorporate — Trismik would need cost-per-token data as a key switching signal

Related to

Databricks AI: Agent Bricks and Unity AI Gateway Databricks Unity AI Gateway addresses model governance and routing at enterprise scale, overlapping with Trismik's evidence-based switching in the same infrastructure category
Comparing 11 Different AI Models Comparing 11 AI models is exactly the kind of empirical benchmark data that an evidence-based model switching platform like Trismik would consume to inform routing decisions
OpenRouter is Joining Stripe OpenRouter provides multi-model access infrastructure; Trismik's evidence-based switching layer is complementary and could be positioned as a decision layer on top of routing infrastructure like OpenRouter

Develops into

i wanted a more physical way of switching models so I made this mini app... sound on Both address model switching UX, but Trismik formalizes it with evidence-based data-driven decisions while the mini app takes a tactile/physical approach — Trismik represents the more systematic evolution of the same core need

Supported by

GPT-6 Astra System Card Trismik's evidence-based model switching requires structured knowledge of model capabilities and safety profiles; the Astra system card provides exactly this kind of authoritative documentation for informed switching decisions.
The Analytical AI Handbook The handbook's evaluation methodology for LLM-based systems provides the principled foundation for evidence-based model switching decisions that Trismik implements
vLLM v0.28.0 Release vLLM's improved inference capabilities enable evidence-based model switching tools like Trismik by making multi-model serving more efficient and cost-effective
Evaluating LLM Judge Agreement and Reliability Trismik's evidence-based model switching depends on reliable model evaluation signals; understanding when LLM judges agree and can be trusted underpins evidence-based selection systems.
Hugging Face Security Contact Information Trismik's evidence-based model switching involves evaluating trustworthiness of AI models hosted on platforms like Hugging Face, where security contact infrastructure underpins trust in the hosting ecosystem
SWE-2: Advanced Coding Model with Improved Cost-Capability Tradeoff SWE-2's cost-capability positioning provides concrete data for evidence-based model switching decisions, as Trismik's approach depends on knowing which models excel at which tasks at what cost

Mercury 2.5 Release Both relate to AI framework/model switching and evaluation infrastructure that developers use when choosing between AI tools
@@ for Mac - AI Agent Launcher Both tools address model/agent selection workflows - Trismik switches models based on evidence while @@ provides a unified launcher that could route to different AI agents based on context
Nari Labs Leads Coval's Voice AI Benchmarks Both focus on evidence-based evaluation and benchmarking of AI models to guide selection decisions — Coval's benchmarks for voice AI and Trismik's evidence-based model switching serve similar purposes of helping users choose the best-performing model
Skillbay: AI Skills Marketplace Trismik uses evidence-based model switching based on performance signals — Skillbay similarly applies evidence standards (before-and-after proof) to validate skill submissions, both representing evidence-driven quality assurance in AI tooling
Introducing System One Models and Jev Trismik's evidence-based model switching and TypeSafe AI's System One Models both address AI infrastructure decisions around model selection and deployment strategy
OpenCodex: Universal LLM Provider Proxy Both address the problem of LLM provider flexibility — OpenCodex enables switching between providers at the proxy level, while Trismik switches models based on evidence/performance; both abstract away provider lock-in
AlphaGenome Variant Analysis Both involve evidence-based model evaluation and switching — Trismik selects models based on performance evidence while AlphaGenome compares variant impact signals across multiple biological evidence tracks (DNase, RNA) to assess functional consequence.

Type:	link
First published:	Thursday, 20 August 2026 at 18:16 UTC
Location:	https://trismik.com/
URL:	https://mattwood.fyi/i/600e99ec

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Connections