/ Kiz8/ Research desk/ 2026

Tech
review.

Field-tested research from the Kiz8 desk. Each technology gets its own deep-dive — vendor catalogs, company cards, founder profiles, and market data. Structured for comparison, not a feed.

0 technologies·0 ready·Last update 2026-05-18

02
/ on the desk

Coming up.

Next technology reviews are in research. Each will follow the same structure — vendor data, company cards, founders, market — once the dataset is ready.

Queued

Agent Frameworks

/ How agents are built.

Frameworks for building autonomous agents — planning, tool use, multi-agent orchestration.

Coming soon

Queued

Foundation Models

/ What agents think with.

Frontier LLMs and their host APIs — context windows, tool use, multimodal, pricing per token.

Coming soon

Queued

LLM Observability

/ Why agents fail.

Tracing, evaluation, prompt diffing, cost monitoring — the layer that turns agent runs into debuggable artifacts.

Coming soon

Queued

Evaluation Frameworks

/ Did the agent do the job.

Tooling for grading model output — task-specific, golden-set, LLM-as-judge, regression suites.

Coming soon

Queued

RAG & Retrieval

/ What agents remember.

Vector stores, embedding pipelines, and retrieval frameworks that ground agents in private data.

Coming soon

Queued

Browser Automation

/ How agents click.

Browser sandboxes, agentic web drivers, scraping toolkits — the surface for agents to act on the open web.

Coming soon

/ contribute

Saw something worth a deep read?

Send us tips, technologies to profile, sandboxes worth tearing apart, or a market dataset you wish someone would publish. We’ll do the dig.