Sean Er

Building @lightsagehq

[Sean Er @sean__er]

https://t.co/KaDd9HGx6j now has evals across 4 harnesses 👀

[Jun @jun_liang_sf]

Yesterday we ran Gemini 4 Argon (Google Antigravity) on the same 92 live APIs as Claude Code, Codex and Muse.

Nearly 8 in 10 APIs got roughly the same score from all four agents.

Same #1 on all four leaderboards in 12 of 24 categories:

Payment: @stripe
Voice STT: @AssemblyAI
Voice TTS: @ElevenLabs
Document Parsing: @reductoai
Durable Workflow: @PrefectIO
Email: @resend
Observability: @datadoghq
Cloud Hosting: @render
Meeting Bot: @meetstreamai
Unified API: @merge_api
Video Infra: @MuxHQ
Voice Infra: @AgoraIO

@ryanseams, @raunakdoesdev, @zenorocha, @ojusave, @shensi, @aidan_timmerman, @lightsagehq

@

[Sean Er @sean__er]

Agent Experience is going to be huge in 2027 as interacting with businesses and products through agents becomes mainstream

Companies not thinking about this are gonna get left behind

Excited to be building this future with @lightsagehq @jun_liang_sf

[Jun @jun_liang_sf]

Can Claude Code and Codex actually use your API? (October Edition)

Only 17 out of 121 APIs scored 80+. Is yours one of them? I ran Claude Code (Sonnet 5) and Codex (GPT-6 Sol) against 120+ live production APIs. 1000+ eval runs. 36 categories. > $5000 spent. A real-world developer use case for every API, and their own isolated sandbox. This is the most comprehensive run we've ever done.

Claude Code and Codex has its own category leaders.
- Payment: @stripe
- Search: @firecrawl
- Sandbox: @daytonaio
- Inference: @OpenRouter
- Auth: @WorkOS , @auth0
- Vector DB: @trychroma
- Voice TTS: @ElevenLabs
- Voice STT: @DeepgramAI
- Voice Telephony: @Telnyx
- Document Parsing: @reductoai
- Browser: @browserbase
- Email: @agentmail
- Graph DB: @neo4j
- Meeting Bots: @meetstreamai
- Durable Workflow: @PrefectIO

Honourable mentions: @AssemblyAI , @Vapi_AI , @temporalio , @FireworksAI_HQ , @superserve_ai, @resend , @pinecone , @recallai , @PayPal , @Tiny_Fish

Full evals at https://t.co/RoAYrnP9ln. Scores are based on discoverability, usability, tool calls, and errors.
*All runs are independent and in isolated sandboxes, powered by @lightsagehq Agent Experience infrastructure.

@ericciarla @zenorocha @ivanburazin @adisingh @rauchg @grinich @aditabrm @vedantvyas

[Kushal Byatnal @kushalbyatnal]

introducing operator-1, an autonomous document extraction agent

operator-1 saturates multiple 3rd party benchmarks, and delivers the most accurate performance on complex tasks that other solutions can't handle:

> long tables with thousands of rows
> lengthy files with context scattered across hundreds of pages
> dense diagrams and images
> much more!

operator-1 is a specialized agent we built that:
- runs within a custom workspace
- knows how to use dedicated tools (parse, search, zoom, code execution, validation) to handle any document
- learns via persistent memory

[Sean Er @sean__er]

@kushalbyatnal lets gooo extend!!

[TinyFish @Tiny_Fish]

We set a goal of 100,000 users by October. Today we crossed 300,000.

The first 100K users took four months.
18 days to 200K.
10 days to 300K.

Every milestone came faster than the last, and it held up because of months of work our team put in before anyone was watching:

https://t.co/mesJNIzkSm

[Sean Er @sean__er]

@Tiny_Fish let's goooo tinyfish!!

[Sean Er @sean__er]

@kaichensf @jun_liang_sf @lightsagehq @nexusvp thanks for the support @kaichensf !!

[Sean Er @sean__er]

@etienneratty @jun_liang_sf @lightsagehq @nexusvp thanks @etienneratty ! appreciate the support :)

[Sean Er @sean__er]

@GTG_llama @jun_liang_sf @lightsagehq @nexusvp @GTG_llama PLG -> ELG -> ALG 🔥

[Sean Er @sean__er]

@yapyuhan @jun_liang_sf @lightsagehq @nexusvp thanks @yapyuhan !

[Sean Er @sean__er]

@graceekongg @jun_liang_sf @lightsagehq @nexusvp thanks @gracekongg :) appreciate the support

[Sean Er @sean__er]

@samuelekpe @jun_liang_sf @lightsagehq @nexusvp Thanks @samuelekpe !

[Sean Er @sean__er]

@richardt830 @jun_liang_sf @lightsagehq @nexusvp Thanks richard! Great meeting you :) Optimize your business for agents is already being the reality. Excited to be building for that future.

[Sean Er @sean__er]

We just raised $4M at @lightsagehq, led by @nexusvp, to build the growth stack for internet’s newest customer: AI agents.

AND

We are hiring!! https://t.co/Dg3eyCsFQe

Full article: https://t.co/WV6UIRrjXq

[Lightsage (formerly Sapient) @lightsagehq]

Excited to be building the Infra for Agent-Led Growth! 🔥

[Hubert Thieblot @hthieblot]

This man is 100% the next Steve Jobs

[Morgan @morganlinton]

Don’t sleep on speech-to-speech.

[Sean Er @sean__er]

@7xuanlux @cursor_ai yeah, i think the key difference is that i enjoyed a terminal native experience as a developer rather than something like codex so i built my own rust terminal multiplexer

the fact that it works on a less powerful macbook makes me more confident it'll work for other users on mac

[Sean Er @sean__er]

Hi, I’m Sean. I built Amorphous after Cursor (@cursor_ai) kept crashing my 16GB M1 MacBook Pro with 2 windows + 6 Claude Code sessions.

It’s a Rust app for parallel AI coding agents, task notes, and terminals.

My commit pace doubled since Feb 2026.

Building this in public.

[Sean Er @sean__er]

@dviolite @cursor_ai it's insane how much more productive you can be by jumping around tasks