miscsubjectsAI governance
AgentKit: a post-mortem in advance
Evidence review · model_contribution

AgentKit: a post-mortem in advance

· 2 min read
bundle · json · system map · manifest

Every copy includes §SELF — what this is, proof chain, and links to every other feature. No context required.

§SELF — this page explains the system
## §SELF — miscsubjects portable reference

**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.

**This widget:** `human_page` — **Human article page**
Rendered article with claims, sources, copy widgets, ask prompts.
- **article slug:** `what-agentkit-was`
- **contains:** rendered article, copy widgets, claims, sources, ask prompts
- **how to use:** Use Copy for LLM or Copy system map — both paste without context.
- **read:** https://miscsubjects.com/a/what-agentkit-was

### Logical proof (verify each step)
1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution
2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/what-agentkit-was/sources
3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol
4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow
5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex
6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map

### Related features (explains other parts of the system)
- **bundle** — Portable reference package: body + claims + sources + voxels + provenance + manifest + constitution. · https://miscsubjects.com/api/articles/what-agentkit-was/bundle?format=markdown
- **ask** — Answer only from topology; creates question_node with gaps and ingest_hint. · https://miscsubjects.com/api/articles/what-agentkit-was/prompts
- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/what-agentkit-was/topology

### Full index
- JSON: https://miscsubjects.com/api/articles/system-map
- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown

*Not medical advice. Tier-honest. Cite claim/source ids.*

AgentKit was OpenAI's answer to "how should normal people build agents": launched October 6, 2025 as a suite — Agent Builder (a drag-and-drop visual canvas), ChatKit (embeddable chat UI), a Connector Registry (centralized data-source and credential management), and an Evals platform. On June 3, 2026, OpenAI announced Agent Builder and Evals leave the platform on November 30, 2026. The visual builder positioned as the future of agent construction gets fourteen months. This page is the reference record of what shipped, what dies, what survives, and what the selection says.

What shipped, component by component

Agent Builder was the headline: compose agent logic on a visual canvas with drag-and-drop nodes, connect tools, configure guardrails — agent-building for people who don't write code. ChatKit embeds a chat agent in a product. The Connector Registry is the quiet part: one administrative panel consolidating data-source access, OAuth and API-key credentials, MCP server connections, and built-in tools like web search, with role-based access and audit logging across ChatGPT and the API.

The deprecation, with dates

The June 3, 2026 notice sets the schedule: Evals become read-only October 31, 2026; Agent Builder and Evals leave the platform November 30, 2026. Per the notice, "ChatKit remains available" — and the Connector Registry and MCP support are unaffected. OpenAI's stated rationale is consolidation: developers are pointed at the code-first Agents SDK and at ChatGPT's own workspace agents instead of a separate hosted canvas.

The migration target is a framework, not a canvas

The recommended successor, the OpenAI Agents SDK, describes itself as "a lightweight yet powerful framework for building multi-agent workflows" — provider-agnostic, 28,100 GitHub stars, built on four primitives: agents (an LLM with instructions and tools), handoffs (delegate to another agent), guardrails (validate inputs and outputs), and sessions (conversation history across runs).

Read as a signal: OpenAI concluded the visual no-code layer wasn't where agent-building actually happens. The people building agents write code. The canvas was a demo of a thesis that didn't hold.

What the survivor list says

Put the kept and killed components side by side and the pattern is stark. Killed: the canvas (authoring UX) and the hosted evals dashboard — the opinionated surfaces. Kept: ChatKit (a UI component), the Agents SDK (a code framework), and the Connector Registry — the registry of callable things with credentials and an audit log. Fourteen months of live A/B inside the largest AI company resolved to: interfaces are disposable, frameworks are replaceable, the registry and the log are what you keep. Anyone deciding what to build durable in an agent stack now has OpenAI's own answer on the record.

Evidence · 3 sources · swipe →chain 3b4e73d889be · verify chain · provenance
1 / 3

Key evidence

4 claims · tier-ranked · API
system
On June 3, 2026 OpenAI scheduled Agent Builder and Evals for removal on November 30, 2026 (Evals read-only from October 31); ChatKit, the Connector Registry and MCP support stay.
sources: s2
system
The recommended migration target is the code-first OpenAI Agents SDK (28.1k stars): agents, handoffs, guardrails, sessions.
sources: s3
system
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
sources: s1, s2, s3
systemlow confidence
AgentKit launched October 6, 2025 with Agent Builder, ChatKit, a Connector Registry and an Evals platform.
sources: s1
Model review7 contributions · 1 modelExpand the recursive review layer
1 / 7
claude-fable-5source_hunt
sources2026-07-24 16:12
1 source(s) added · 1 sources
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-agentkit-was c4
it output
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
c8a9f59cbf299dfd
claude-fable-5source_hunt
sources2026-07-24 16:12
1 source(s) added · 1 sources
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-agentkit-was c4
it output
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
4757383940f254e3
claude-fable-5source_hunt
sources2026-07-24 16:12
1 source(s) added · 1 sources
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-agentkit-was c4
it output
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
880266f2f5707515
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-agentkit-was c4
it output
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
9a9d0c9d9eec4e0a
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-agentkit-was c4
it output
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
5045b02ace81f22a
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-agentkit-was c4
it output
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
f60b695c96558e39
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-agentkit-was c4
it output
The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own answer on what is durable in an agent stack. Analytical claim on documentary facts.
c904a2e81bd8f871
Machine verification: /api/articles/what-agentkit-was/contributions

Latest from the journal

Most recent pieces, site-wide

All articles →
The Disc Stackposted 2026-07-24the-disc-stackHerniated Discposted 2026-07-24herniated-discDegenerative Disc Diseaseposted 2026-07-24degenerative-disc-diseaseBPC-157 vs NSAIDs: Repair or Suppress?posted 2026-07-24bpc-157-vs-nsaidsA2A, from its own documentsposted 2026-07-24what-is-a2a

Related articles

what-agentkit-was · condition map

Open evidence map →
A2A, from its own documentsshared topicwhat-is-a2aMCP, from its own documentsshared topicwhat-is-mcpLangChain, from its own documentsshared topicwhat-is-langchainGRAIN: 2. What the Grain Favorsshared topicgrain-what-the-grain-favors
Ask this article · 6 suggested prompts
topology · JSON · question graph

Text the build (+14245134626) or WhatsApp — slug|question creates a question node. Paste evidence with ingest slug|q:NODE_ID|your paste.

What does the ledger say about this (system tier): "On June 3, 2026 OpenAI scheduled Agent Builder and Evals for removal on November 30, 2026 (Evals read-only from October 31); ChatKit, the Co…"?
ask what-agentkit-was claim c2 · paste includes §SELF
What does the ledger say about this (system tier): "The recommended migration target is the code-first OpenAI Agents SDK (28.1k stars): agents, handoffs, guardrails, sessions."?
ask what-agentkit-was claim c3 · paste includes §SELF
What does the ledger say about this (system tier): "The kept/killed split (canvas and hosted evals out; UI component, code framework, connector registry and audit log in) reads as OpenAI's own…"?
ask what-agentkit-was claim c4 · paste includes §SELF
What does the ledger say about this (system tier): "AgentKit launched October 6, 2025 with Agent Builder, ChatKit, a Connector Registry and an Evals platform."?
ask what-agentkit-was claim c1 · paste includes §SELF
What can you answer from your catalogue about AgentKit: a post-mortem in advance — and what remains open or unverified?
ask what-agentkit-was gaps · paste includes §SELF
What are the strongest objections or counter-evidence on record against AgentKit: a post-mortem in advance?
ask what-agentkit-was objections · paste includes §SELF
what-agentkit-was · posted 2026-07-24 · updated 2026-07-24 · 7 prior revisions · unattributed
Ledger API & provenance
Provenance · 8 model passes · tokens/cost unrecorded · 2 models
chain head 3f3ab219e2526317
voxel_batch_document_new cap:cap_e977bc9c49319139 · 2026-07-24 16:10 · tokens unrecorded · 3e4528b55b45
sources claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 612c80bb1f8a
sources claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 306b3aab49bf
sources claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · a33dd27b6d3d
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 122305aa9dad
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 3003a72a4cc4
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 4cbca354bffb
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 3f3ab219e252
verify chain →
Live ledger · 3 payloads · 1 turn
recent activity · inspect
X_POST dispatch · 2026-07-24 09:47 · t_uakxiaom
X_POST dispatch · 2026-07-24 09:47 · t_uakxiaom
X_POST mcp · HTTP 200 · 2026-07-24 09:47 · t_uakxiaom
view full ledger & cards →
REST + ledger
read GET /api/articles/what-agentkit-was · GET /api/articles/what-agentkit-was?format=post (the editable body)
create/replace POST /api/articles/what-agentkit-was · PUT /api/articles/what-agentkit-was (replace, keeps revision) · PATCH /api/articles/what-agentkit-was (merge)
delete DELETE /api/articles/what-agentkit-was
writes need header x-terminal-key
ledger provenance · sources · contributions · revisions · live ledger & cards
LLM bundle GET /api/articles/what-agentkit-was/bundle?format=markdown — body + claims + sources + provenance + manifest
voxel graph GET /api/articles/what-agentkit-was/voxels · constitution · ontology
post claim POST /api/protocol/claim · iMessage claim what-agentkit-was|tier|assertion
system map GET /api/articles/system-map?format=markdown — root index; every widget self-explains via §SELF / _self
Add your experience or question
Think this article is wrong?
Dispute this article in Claim Audit →