pragma.vision Your technology observatory

Verification register Compute & Web Infra

Readiness verdict

agentgateway

A dated reading of what is claimed, reported, and independently verified in the current evidence.

As of
2026-06-28
Revision
1
Method
v1.0.0

Current reading

The readiness gap, in one scan

AI-assisted assembly · derived results

Claimed
70

Public ambition and stated capability

Reported
68

Observed practitioner reporting

Verified
62

Independently supported evidence

Gap
+8

Claimed minus verified

Evidence strength Critical

Decision

What the current evidence supports

Human editorial judgment · 2026-06-28

Proceed with caution

Why
Directly relevant — pragma.vision runs multiple mcp-* servers and AP2/A2A protocol surfaces, and agentgateway is the canonical Gateway API Inference Extension agent backend. Strong LF/vendor backing and real benchmarks, but a roughly year-old project still in active development with stateful-MCP and auth-refresh caveats argues for guardrails, not a drop-in (Rules #2, #7, #14).
Next
Pilot in a non-prod path as an MCP/LLM egress proxy for one mcp-* server; validate multi-instance session handling and JWKS refresh before fronting any authenticated agent traffic.

Constraints

Blockers

No named blocker is present in the current public projection.

Evidence summary

Derived counts

AI-assisted assembly

Total
8
Tier 1
3
Tier 2
2
Tier 3
3
Supports
4
Contradicts
3
Context
1
Latest observed
2026-06-25

Counts and dates only. Raw signals, private excerpts, trust records, and internal corpus material are not published here.

Publication record

Revisions

Initial public reading

This is the initial public reading. No earlier readiness change is recorded.

Your opinion

Tell us anything.

What works, what doesn't, what's missing — especially about our watches, lenses, and the register itself. Anonymous is fine; leave an email if you'd like a reply.