Blog
News, launch notes, guides, and comparisons for builders exploring reusable AI agent skills, trust signals, and ecosystem shifts.
Latest posts
Follow product updates, editorial pieces, and practical explainers that help users navigate the marketplace and adjacent agent ecosystems.
-
Use Prompt Flow for LLM workflow testing and evaluation
Build a Prompt Flow graph, run interactive and batch tests, inspect traces and evaluation metrics, and promote only reviewed LLM workflow versions.
-
Serve local model endpoints for agent tests with OpenLLM
Launch an OpenAI-compatible OpenLLM server for a chosen open model, point an agent runtime at it, and compare behavior before production use.
-
Run supervised Suna sessions for reviewable agent work
Start a bounded Suna or Kortix agent session, let it use browser, files, tools, and connectors, then review the session output before delivery.
-
Monitor and evaluate LLM agent traffic with Helicone
Route model calls through Helicone, inspect costs, latency, traces, prompts, and evaluations, then review changes before they ship.
-
Build graph RAG context with Neo4j LLM Graph Builder
Convert a bounded document set into a Neo4j knowledge graph, inspect extracted nodes and relationships, and use it for graph-backed RAG.
-
Match resumes to job descriptions with Resume Matcher
Run a reviewable resume-to-job-description matching workflow that produces ATS-style gaps, keyword suggestions, and human-checkable resume improvements.
-
Evaluate and monitor LLM workflows with Agenta
Run prompt experiments, testset evaluations, and observability reviews for production LLM workflows before regressions reach users.
-
Build graph-based retrieval workflows with GraphRAG
Index private text into graph-backed retrieval structures, tune prompts, and query the resulting knowledge graph for RAG workflows.
-
Constrain agent outputs with Outlines structured generation
Force LLM outputs into typed schemas, enums, JSON-like structures, and routing records during generation instead of repairing malformed text afterward.
-
Prepare local retrieval embeddings with FastEmbed
Generate dense, sparse, image, and reranking embeddings locally before writing vectors into Qdrant or another retrieval stack for agent memory and RAG workflows.