Skip to content

Project

Notion

Notion is a workspace platform combining notes, documents, wikis, and databases, with an API and MCP integrations for AI agents and external tools.

Known aliases

  • Notion API
  • notion.com
  • Notion Custom Agents
  • Notion database
  • Notion DB
  • Notion Labs
  • Notion MCP
  • notion.so

Current stories

buildOne report1 publisher

An empty page 1 in Apple's review feed made a scraper report zero Spotify reviews, its author says

Apple's undocumented App Store review feed returns well-formed pages with zero entries inside its 10-page range, a DEV Community post reports. A scraper that breaks on the first empty page can report no reviews for an app that has them.

Publishers:dev.to

Reality

Evidence35
Adoption
Not scored
Hype gap−10
Incentives30
Confidence50
buildOne report1 publisher

Turbopuffer v3 demotes the ANN index to one secondary index among several

Turbopuffer is rewriting its serverless database as v3, moving the ANN index out of the core of storage and making it one of several secondary indexes. A dev.to explainer of the September 30 post says the vector-first layout held back GROUP BY and aggregation queries.

Publishers:dev.to

Reality

Evidence40
Adoption25
Hype gap+35
Incentives45
Confidence50
buildOne report1 publisher

Notion's ZeroEntropy deal ends the reranker maker's run as a standalone API vendor

Notion bought ZeroEntropy after its reranker cut latency in Notion's reranking step by 85%, by Notion's count. The hosted product is being sunset with an open-weight release, so teams that built on ZeroEntropy's API now have to decide where the model runs.

Publishers:runtimewire.com

Reality

Evidence40
Adoption40
Hype gap+15
Incentives60
Confidence45
productOne report1 publisher

Sign in with ChatGPT brings a user's AI allowance into 16 partner apps

OpenAI's new Sign in with ChatGPT lets people carry their identity and existing AI allowance into third-party apps, starting with 16 launch partners. For product teams, new users arrive signed in with AI budget to spend, and OpenAI holds both.

Publishers:techcrunch.com

Reality

Evidence45
Adoption25
Hype gap+30
Incentives65
Confidence50
productOne report1 publisher

Momentic's Mo offers a prompt and a URL in place of maintained test scripts

Momentic launched Mo, an agent swarm that tries thousands of edge cases on a live app so developers can stop maintaining test scripts. For a QA lead, the open decision is whether that exploration can replace the checks a team reruns after every change.

Publishers:siliconangle.com

Reality

Evidence35
Adoption15
Hype gap+45
Incentives70
Confidence40
leadershipOne report1 publisher

Business Insider testers lost 8 pounds and a Notion schedule when an AI agent acted for them

Instinct, an AI agent Business Insider staff tested, paid 8 pounds for the wrong Oxford congestion charge and wiped an editor's Notion schedule. Its research held up, so the thing to settle before delegating is what the agent may do without a person checking first.

Reality

Evidence45
Adoption
Not scored
Hype gap+10
Incentives
Not scored
Confidence40
securityOne report1 publisher

Anthropic opens a public storefront for more than 2,000 Claude connectors and plugins

Anthropic's Claude Marketplace is live with more than 2,000 connectors and plugins, including ones published by Atlassian, Google, Microsoft and Salesforce. Each connector enabled from it adds a supplier that belongs in third-party and access reviews.

Reality

Evidence40
Adoption
Not scored
Hype gap+15
Incentives60
Confidence45
productOne report1 publisher

Notion says its editor dropped one of two edits to the same block until 2025

In an engineering post, Notion says its server used to keep whichever update to a block arrived last. Pages felt collaborative anyway, because each paragraph is stored as its own database record. The fix is a CRDT.

Publishers:notion.com

Reality

Evidence58
Adoption30
Hype gap+12
Incentives68
Confidence55
buildOne report1 publisher

Where the check lives decides how far a wrong agent write travels

Sanity blocks published writes by API default, Notion records Custom Agent runs in its Enterprise audit log, and Supabase tells developers to keep its MCP server off production. None of the three tests whether the value is right.

Publishers:dev.to

Reality

Evidence56
Adoption38
Hype gap+14
Incentives72
Confidence52
buildOne report1 publisher

Five hours of monthly maintenance ate a 40% cut in an eleven-tool SaaS bill

A five-person team swapped eleven paid subscriptions for self-hosted open source and came out close to level, because the cost that mattered was the maintainer's own hours.

Publishers:dev.to

Reality

Evidence30
Adoption15
Hype gap+20
Incentives55
Confidence40
buildOne report1 publisher

The portable Agent Plugins manifest puts OpenAI's extras under extensions.com.openai

OpenAI's plugin docs define one root manifest and a single directory shared by ChatGPT and Codex, while the built-in scaffold still writes the older .codex-plugin layout and an MCP file that needs converting.

Reality

Evidence62
Adoption28
Hype gap+10
Incentives78
Confidence52
buildOne report1 publisher

Mapbox's Agent Toolkit lets a model add a stop to a route the driver is already driving

Mapbox's September 17 release turns live traffic and a 250-million-place index into function calls an agent invokes for itself. Who is allowed to invoke them is still the integrator's problem.

Publishers:runtimewire.com

Reality

Evidence38
Adoption30
Hype gap+28
Incentives76
Confidence55
buildOne report1 publisher

A bigger platform shipped the feature in three of five AI closures with a stated cause

Relay stopped operating on Monday after OpenAI and Google added the same workflow-agent capability to their own products. Two of the other four closures in the same account went the same way, and the 42% failure figure quoted alongside them counts something else.

Publishers:mezha.net

Reality

Evidence30
Adoption38
Hype gap+30
Incentives25
Confidence35
productOne report1 publisher

TechCrunch's AI graveyard blames platform encroachment for one death in nine

Relay shut down on Monday after five years, outpaced by automation OpenAI and Google built into their own tools. The other entries on the list failed on cost, retention, privacy or engineering, and S&P Global counts competition as one abandonment cause in five.

Publishers:techcrunch.com

Reality

Evidence45
Adoption30
Hype gap+15
Incentives40
Confidence55
productOne report1 publisher

Meta's Muse decides for itself which actions need your consent

Meta's first consumer agent ships as its own app, with connectors for services like Google and Spotify, a Stripe-handled card link, and a permissions screen set to ask about only some actions. The model-training control starts selected.

Publishers:engadget.com

Reality

Evidence55
Adoption12
Hype gap+22
Incentives62
Confidence52
buildOne report1 publisher

Sharing an MCP server across a team now costs an OAuth 2.1 authorization flow

The auth overhaul in the final MCP spec reaches only remote transports, which turns a compliance question into a question about deployment topology, and even the vendors credited with getting ahead of it need checking.

Publishers:dev.to

Reality

Evidence38
Adoption45
Hype gap+28
Incentives55
Confidence45
investOne report1 publisher

Anthropic alone could raise four times what the first half's other 57 IPOs did

Crunchbase counts 58 billion-dollar venture listings in the first half against 27 a year earlier, but $86bn of the $110.8bn raised was SpaceX, which leaves the autumn calendar to prove the depth.

Reality

Evidence52
Adoption64
Hype gap+31
Incentives76
Confidence46
investOne report1 publisher

Notion hires roughly 330 people into a company already running 700 agents

A 30% headcount increase against $500m of revenue takes revenue per employee from about $455,000 toward $350,000, so the plan only works if the AI line, already more than half of sales, grows about as fast as the payroll.

Reality

Evidence22
Adoption55
Hype gap+38
Incentives74
Confidence30
buildOne report1 publisher

Lever's bare array makes the naive jobs[] parser return zero roles forever

Three of the four public ATS endpoints wrap their list in a jobs key, so the parser passes its first test and then reports an empty array whether the vendor is wrong, the board is empty or the upstream threw a 502.

Publishers:dev.to

Reality

Evidence64
Adoption32
Hype gap+12
Incentives70
Confidence60

Earlier coverage

  1. Plaud's cellular earbuds hand the recording-consent problem to employers

    Product · August 27, 2026 · Confirmed4 publishers