Tagged “Agents”

7 posts · View all tags
MCP's Fix for Bloated Tool Catalogues Has a Bill Attached — And It's in the Docs, Not the Roadmap
Agents & Protocols

MCP's Fix for Bloated Tool Catalogues Has a Bill Attached — And It's in the Docs, Not the Roadmap

The MCP roadmap names tool-catalogue bloat as a priority. The client documentation already ships the fix — progressive discovery, with a search_tools meta-tool — and the same page warns that it can cost more than it saves, because loading definitions mid-conversation invalidates the provider's prompt cache. Three layers of caching, only one of which the protocol actually specifies, and the one that bites belongs to your model provider.

September 7, 20267 min read
Read more
LangChain Just Made MCP First-Class — We Ran It the Same Day, and Three Things Don't Work Yet
Agents & Protocols

LangChain Just Made MCP First-Class — We Ran It the Same Day, and Three Things Don't Work Yet

MCP support moved into the langchain package today, built on FastMCP, with elicitation as a LangGraph interrupt and a cacheable tool catalog. We installed it the same afternoon and pointed it at a server we wrote against the new spec. The announcement is accurate; the ecosystem around it hasn't caught up, and one of the gaps turns a human-approval gate into a sentence the model makes up.

September 3, 20269 min read
Read more
An agent can narrow its own web search, but never widen it
Agents & Protocols

An agent can narrow its own web search, but never widen it

AWS gave agent web search a list of allowed sites on 19 August. The admin sets one list, the agent can set another, and when they disagree the agent's list can only make the search smaller. That one rule is the difference between a guardrail and a note in the prompt.

August 26, 20264 min read
Read more
Spec-Driven Development: is it the solution to Vibe Coding?
Agents & Protocols

Spec-Driven Development: is it the solution to Vibe Coding?

A GitHub toolkit with 127k stars says you should write the spec before the code, and let the agent build from it. I ran it, then read the two engineers who tested it properly — and both reached for the same comparison: the last time our industry tried generating code from documents.

August 14, 202612 min read
Read more
Muse Glimmer: a 30B agentic model that runs on one GPU, no data center required
Models

Muse Glimmer: a 30B agentic model that runs on one GPU, no data center required

Meta released a 30B multimodal model built for local agent workloads — beats Gemma4 and holds its own against Qwen3.6 on agentic benchmarks, and fits on a single consumer GPU. Here's what's actually new, and what it'd take for it to land on WEC.

August 10, 20264 min read
Read more
'Loop Engineering Is Dead' — and the Real Story Is Weirder Than the Obituary
Agents & Protocols

'Loop Engineering Is Dead' — and the Real Story Is Weirder Than the Obituary

In June, 'loop engineering' got a name. Six weeks later it was declared dead — and the industry answered with vendor guides, competing definitions, and a wave of SEO. Here's what loop and graph engineering actually mean, why a free MIT textbook settles the argument on page 189, and what a six-week hype cycle should teach you about what to learn.

August 5, 202612 min read
Read more
MCP Just Shipped Its Biggest Update Ever — Here's What Actually Changes for AI Agent Engineers
Agents & Protocols

MCP Just Shipped Its Biggest Update Ever — Here's What Actually Changes for AI Agent Engineers

The 2026-07-28 MCP specification rips out sessions and rewrites authorization. If you build or run MCP servers, this changes your infrastructure, your auth flow, and your deprecation clock — whether you asked for it or not.

July 28, 20265 min read
Read more