121 Photos and videos
I wrote a short post on what Summation’s MCP connectors unlock.
Business questions rarely live in one system. With MCP connectors, Addison can reach the tools where context lives: Salesforce, NetSuite, Drive, Slack, and more.
The goal: decision-grade answers, not more assembly.
summation.com/resources/your…
8,096
RC retweeted
Add this shortcut to your iOS Home Screen so you can search for Codex. And use this icon raw.githubusercontent.com/lo…
icloud.com/shortcuts/857005f…
7
10
103
28,716
RC retweeted
Jun 9
Summation was founded for this exact reason - standard LLMs don't work for CFOs. They need numbers they can trust.
Every metric in a Summation report is traceable.
Every insight in a Summation workflow is verified.
Thanks @BatteryVentures for conducting the survey and for the callout!
AI adoption in finance is hitting a wall. We surveyed 129 CFOs and finance leaders to find out why.
The top concerns: 71% say AI models aren't accurate enough to trust, 44% worry about cost and 36% can't justify the ROI. On the adoption side, integration complexity and skills gaps on the finance team top the list of barriers.
Yet 95% are still willing to pay a premium for tools that actually work. CFOs want AI and they're willing to spend on it — the products just aren't delivering yet.
Read the full survey findings for a breakdown of what it will take to close the gaps: okt.to/OTft1J
2
8
199
"We recently submitted a confidential S-1. We expect it to leak so we’re just announcing it." :)
openai.com/index/openai-subm…
1
29
RC retweeted
May 27
Most GTM leaders make the call when it's too late.
A weekly GTM review needs:
1/ Pipeline coverage PipeGen
2/ Rep activity attainment
3/ Where leadership should intervene
@_summation generates the readout, so leaders spend Monday acting, not stitching.
👉Weekly GTM readout: app.summation.com/public/prj…
3
7
282
This is a sharp idea: turn your edits, preferences, and “that’s not quite right” moments into reusable agent training signal
grade.dev
May 22
Hey there, I built something.
I generate a lot of code, docs and analyses with Claude. I got frustrated with the feedback loop that made it hard to give the agent meaningful feedback it could learn from.
You copy-paste comments, you fire up a Google Doc, or you just don't review and ship the slop.
Instead, I built grade (.) dev. A collaborative review tool for AI markdown artifacts. Your agent pushes a markdown doc (prose, code, mermaid) over MCP. You leave comments inline to a specific code line, mermaid node or sentence. The agent reads them back through the same MCP.
I use it to teach Claude my coding style, get a friend input on something, … Kind of a personal RLHF!
If you have been around long enough to remember pastebin: think of grade as the grown up version, built for the agent era.
Free, every review auto-expires. Have fun!
Link👇
1
47
RC retweeted
May 20
Our customer, @OneLineage runs 250 warehouses across the global cold storage network.
KPI anomalies were caught reactively.
Investigations took weeks.
Now they take 15 minutes.
👉New case study: summation.com/resources/line…
2
9
4,576
Same dataset. Same prompt.
Claude generated a Word doc.
@_summation generated a living, collaborative artifact with traceable numbers and verifiable insights.
AI is moving from “content generation” to “decision infrastructure.”
Head to summation.com/try-summation to know more!
May 19
Same dataset. Same prompt: run an MBR.
Claude generated a Word doc.
@_summation built a living artifact — every number traceable, every insight verified, built for teams to collaborate.
→ Try it yourself: summation.com/try-summation
3
12,710
# agent-browser skill and memory leaks
These "Google Chrome Helper" processes were hogging my mac cpu for the past few days.
The following did not help:
1. Suspending all tabs on Google Chrome
2. Closing Google Chrome
3. Closing other Chromium based browsers
Turned out there were orphaned agent-browser automation sessions created by Codex / Claude Code with temp Chrome profiles running for days.
Killed the parent processes and my cpu usage dropped to <10%
75
So far the best product execution of bring your laptop agent sessions to the phone!
You've been asking for this one...
Now in preview: Codex in the ChatGPT mobile app.
Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.
2
54
My biggest issue with AI-generated analysis is not the prose. The prose is usually great.
The problem is everything underneath it.
Do the numbers tie? Are the claims verified? Can the logic be rerun next month?
That is the bar we built Reports for at Summation.
summation.com
1
3
47
116,367
This is worth paying attention to. If you’re building agent sandboxes and need save/restore for filesystem state, Amazon S3 Files is a very interesting new primitive. It gives S3 buckets file system semantics without moving data out of S3, which makes shared agent state and persistent sandbox storage much more practical.
aws.amazon.com/about-aws/wha…
1
122
New blog post: Prompt Caching from First Principles
Most explanations stop at "identical prefixes get cheaper." This one walks through the full transformer pipeline: tokenization, embeddings, KV caching to show exactly why caching works, what breaks it, and the math that makes the savings obvious.
The twist: the blog has an AI co-author built in, I call it "Margin Notes".
Select any paragraph you find dense, and Margin Notes will reframe it for you, as a more intuitive explanation, an analogy, a step-by-step breakdown, or even a quiz. Same content, shaped to how you think.
lossfn.com/blog/prompt-cachi…
1
1
144
The "Margin Notes" function uses @steipete awesome summarize library to find free models available at anytime: github.com/steipete/summariz…
66
RC retweeted
Mar 27
For my friends who are still using UV and might be a little weary about recent compromises to PyPi packages, stick this in your pyproject.toml.
You can let all of those pip users find and report the compromises...
67
487
4,078
287,386
OpenClaw - Perplexity Edition
Mar 11
Announcing Personal Computer.
Personal Computer is an always on, local merge with Perplexity Computer that works for you 24/7.
It's personal, secure, and works across your files, apps, and sessions through a continuously running Mac mini.
74