
RevOps | @merge_api | The context engine for agents
New York
Joined March 2026
- Tweets92
- Following78
- Followers48
- Likes2.3K
Tim Bourcier retweeted
This may be one of the stupidest things I have ever made.
A site that writes your GTA 6 sick-day message for you. Claude drafts it in Slack or Gmail, and you pick how professional it sounds from 1 to 5 stars.
It prompts your claude to connect to your slack and gmail, drafting messages on a scale of 1-5 stars, in ranging professionalism.
go ham renovating jasons house @xqc
gtapto.pages.dev/
Tim Bourcier retweeted
you dont work on bleeding edge stuff if your slack isnt littered with this guy
Tim Bourcier retweeted
Teams across Merge build with Codex and ChatGPT every day. We’re proud to power integrations inside them, too.
OpenAI (@OpenAI) just featured how we’re putting these tools to work, including our dinner bot, powered by GPT-6 Astra and Merge connectors.
We host 2–3 executive dinners a week. Guest lists, outreach, and attendee tracking used to take dozens of hours. Now, they take about 30 minutes per event.
Read more: openai.com/index/merge-build…
Tim Bourcier retweeted
Who's the best @framer designer you know?
Looking for a quick sprint with a tight scope and a very high bar. DM's are open!
Tim Bourcier retweeted
Today we launched the Universal Context Layer at @merge_api.
It turns everything your company knows into one brain that every AI tool and agent shares, so your team can switch assistants without losing any context.
Context is king, we just built its castle.
xitter.cf/merge_api/status/21176…
Your agents are running around blind.
They can't see your Slack, your Notion, or what your team decided this morning.
And you're paying for every wrong turn.
Introducing Merge’s Universal Context Layer: your company's knowledge and skills, turned into one brain that works with any AI tool or agent.
Right now your AI starts from scratch every query. It burns tokens and brings back the wrong answer.
Merge Universal Context Layer lays down one shared trail through everything your company knows.
Every agent works from the exact same company knowledge.
It connects to your Slack, Granola, and Notion in one click, and automatically adds relevant information into your company brain and shares it across any AI assistants your team uses.
It keeps working after you log off at night. By the morning it has suggestions waiting for your approval.
With Merge, your team can switch to any AI assistant they want without losing ANY context.
Merge's Universal Context Layer:
- All harnesses (Claude, ChatGPT, in-house) connect via MCP
- Connect to a single context layer
- Thousands of enterprise-grade tools, both knowledge and live search
- Dreaming improves skills, memory, context retrieval, and actions each night
- Insights help glean how your org is using AI and what can be done better
Your agents are running around blind.
They can't see your Slack, your Notion, or what your team decided this morning.
And you're paying for every wrong turn.
Introducing Merge’s Universal Context Layer: your company's knowledge and skills, turned into one brain that works with any AI tool or agent.
Right now your AI starts from scratch every query. It burns tokens and brings back the wrong answer.
Merge Universal Context Layer lays down one shared trail through everything your company knows.
Every agent works from the exact same company knowledge.
It connects to your Slack, Granola, and Notion in one click, and automatically adds relevant information into your company brain and shares it across any AI assistants your team uses.
It keeps working after you log off at night. By the morning it has suggestions waiting for your approval.
With Merge, your team can switch to any AI assistant they want without losing ANY context.
national geographic for nerds just dropped
Your agents are running around blind.
They can't see your Slack, your Notion, or what your team decided this morning.
And you're paying for every wrong turn.
Introducing Merge’s Universal Context Layer: your company's knowledge and skills, turned into one brain that works with any AI tool or agent.
Right now your AI starts from scratch every query. It burns tokens and brings back the wrong answer.
Merge Universal Context Layer lays down one shared trail through everything your company knows.
Every agent works from the exact same company knowledge.
It connects to your Slack, Granola, and Notion in one click, and automatically adds relevant information into your company brain and shares it across any AI assistants your team uses.
It keeps working after you log off at night. By the morning it has suggestions waiting for your approval.
With Merge, your team can switch to any AI assistant they want without losing ANY context.
Tim Bourcier retweeted
muse wonder is super fast and token efficient ⚡️ ⚡️
give it a go!
The two top models on the Intelligence Index take about twice as long per task: Claude Opus 5.5 and Sonnet 5.5 (@AnthropicAI) vs. Muse Wonder (@Meta).
Muse Wonder finishes an average task in 6.8 minutes with a 52.4 score. Opus 5.5 takes 13.2 and Sonnet 5.5 takes 15.3, scoring 57.6 and 56.0. Muse Spark 1.3 and GPT-6 Astra (@OpenAI) follow at 8.1.
When someone is waiting on the answer, minutes can matter more than a few index points. Merge Gateway lets you send latency-sensitive requests to the fast model and the hard ones to the strong one, behind one endpoint.
Scores via artificialanalysis.ai, week of Oct 12.
Tim Bourcier retweeted
muse wonder full on merge’s intelligence index
Replying to @Meta
@Meta's new Muse Wonder Full debuts third on the Intelligence Index at 55.8, just 0.2 behind Anthropic’s Claude Sonnet 5.5.
Claude Opus 5.5 (@AnthropicAI) still leads at 57.6. Muse Wonder Full also places ahead of OpenAI’s (@OpenAI) GPT-6 Astra (52.7) and Google’s (@Googledeepmind) Gemini 4 Argon (52.6).
Scores via artificialanalysis.ai, Oct 12.
Tim Bourcier retweeted
September flew by at Merge.
Between our billboards, Lenny & Friends Summit, and 8+ dinners, we still found time to ship: Universal Context Layer, new models on Gateway, Batch Requests, and Self-Hosted Models.
Stay tuned for what we've got cooking in October.
Thanks to Jev, you can now write workflows in plain English and run them instantly like code.
I spent the day feeding it descriptions of tasks and it spit out workflows across hundreds of apps faster than I could read them.
An agent could do this already, in 30 seconds, for a dollar, differently every run. Jev does it in two seconds, for free, the same way every time.
























