Tag: Agents

16 NOTES
148

REST APIs for Agents

Index the OpenAPI document. Search across catalogs. Then call one operation.
MCPGOAGENTSOPENAPI
2026-08-30
147

Sessions Left the Protocol. Put the Handle in the Argument.

platform_info mints dps_…; the model threads it. Go SDK v1.7.0, MCP 2026-07-28.
MCPGOAGENTSPROTOCOL
2026-08-28
146

Don't Ingest the CSV. Point Hive at It.

Hive still maps a table name to a directory of files
MCPGOAGENTSHIVE
2026-08-26
145

Don't Sandbox Python. Embed Starlark.

starlark-go in a Go server: FileOptions, host bindings, and a cancel watchdog
MCPGOAGENTSSTARLARK
2026-08-24
143

Do Cross-References Help LLM Agents Complete Documents?

The agent found every page certified unreachable. Links cut search cost and keep working when search is off; they do not change what it reaches
MCPAIAGENTSDATA
2026-08-20
142

Knowledge Pollution: Verification Displacement, Capability, and the Price of a Curation Gate

A wrong note that passed review spread only where the agent could have checked it, and only on Haiku 4.5: 16 of 24, against 0 of 24 on Sonnet 5 and Opus 5
MCPAIAGENTSDATA
2026-08-17
135

An Instrument for MCP Agent Studies

The harness behind two DOI-archived benchmark reports, and why a study premise can be killed in one working day
MCPAIAGENTSDATA
2026-08-01
131

When Do Agents Use Stored Knowledge?

A benchmark that killed its own hypothesis: strong models re-derive what they can check, and a weak model trusts a stale note over the evidence in front of it
MCPAIAGENTSDATA
2026-07-26
128

Does a Semantic Knowledge Layer Make an Agent Measurably Better?

A reproducible benchmark: 42.7% to 98.7% on knowledge-trap questions, and a platform that learns from empty
MCPAIAGENTSDATA
2026-07-22
124

The Agent Gateway to Your Platform: mcp-data-platform

An Apache-2.0 MCP server that gives frontier models access and grounded context to everything you built
KUBERNETESFOSSPLATFORMMCP
2026-07-15
115

When Your Tools Lie to the Agent

I drove my own platform as a real client and told it to find every place a tool said one thing and did another. A case study in MCP SDLC.
MCPGOAGENTSTESTING
2026-06-28
113

Where Tribal Knowledge Goes

An insight an analyst shares mid-session becomes a reviewed, signed-off change to the catalog rather than vanishing when the conversation ends.
MCPAGENTSDATAAI
2026-06-26
111

Steering Agents Without Caging Them

Steering agents from the server middleware instead of the tool descriptions.
MCPGOAGENTSAI
2026-06-24
109

One Process, Many MCP Servers

Compose mcp-trino, mcp-datahub, and mcp-s3 as Go libraries behind one endpoint, instead of running three servers that can't see each other.
MCPGOAGENTSDATA
2026-06-22
107

Why I Build MCP Servers in Go, Not Python

An MCP server faces an agent on both sides. Go lets me leash the agent that writes it and harden the contract the agent reads.
MCPGOAIAGENTS
2026-06-19
81

The Two Failure Modes That Break Your AI Data Agent

A Case Study in Agent Psychology
MCPLLMAIOPENSEARCH
2026-02-26