flavia

Not a real bot. I’m a human being, and I like building things.

[flavia @flaviambot]

@AlfieJCarter Agentes

[flavia @flaviambot]

@MichLieben ads

[flavia @flaviambot]

@AdamrahmanGTM GTM

[flavia @flaviambot]

@shivsakhuja @ycombinator goose

[flavia @flaviambot]

@thesamparr I actually built a skill inside Claude that gets my team actually using it. It detects which tools they have connected, walks them through the rest, recommends workflows & skills for their role, and runs a live demo with real data. Then logs everything to Notion.

[Javi™ @javitm]

We cut an eCommerce AI agent from:

* 34,302 → 10,100 tokens
* 28.16s → 6.76s latency
* ~$19K/mo → ~$5K/mo inference cost

No model change.

Just better agent architecture:

* normalize tool payloads
* whitelist context
* minimal output schemas
* ID-based UI hydration

Optimize the system around the model!

https://t.co/FPvu4E3jXX

[Javi™ @javitm]

Here are the first two real use cases where we successfully applied Autonomous Researcher:

1. Optimizing an e-commerce search engine: the agent searched for the latest information retrieval research papers, generated evaluation datasets and experiments, and tested them with real code. After a month, it achieved ~30% improvement on eval metrics.

2. Extracting article ideas from live Slack conversations: We connected it to a few internal channels. The agent accumulates information in its knowledge base, compares it against state-of-the-art public info, and returns drafts for review. We publish or reject them with reasons; rejections feed back into the knowledge base, improving the odds of interesting ideas next time.

[Javi™ @javitm]

We’ve been experimenting with research agents for a while now and decided to open source Autonomous Researcher — a framework built for long-running agents that accumulate memory, taste, and traceable progress over weeks.

Persistent Knowledge Base with validated Hypothesis → Experiment→ Findings loops, Challenge/Strategic reviews, and durable artifacts that survive interruptions.

Not just faster hill-climbing → deeper, reproducible research.

Works with Codex + Claude Code.

Starter template here → https://t.co/TP6qkQP5Hi

#AIagents #AutonomousResearch #AgenticAI

[flavia @flaviambot]

@businessbarista claude!

[flavia @flaviambot]

@christianrais77 lovable & chatgpt!

[flavia @flaviambot]

@emilahlback @lovable 👋👋👋👋

[The Agile Monkeys @theagilemonkeys]

We hosted an event in NYC called 'AI - The Signal vs. The Noise.' It was fun and full of insightful discussions. We plan on having more so stay tuned. 😎 For no BS AI insights, sign up for our newsletter. https://t.co/8d1zE8jB9s

[flavia @flaviambot]

@Vaughtton @nocodehackers @bubble @robotjuggler @pabloheredia24 Pues a la próxima me apunto seguro!! Que vaya todo genial🤘🤘

[flavia @flaviambot]

@alenanik11 😂😂😂 Hey Jorge!! en @theagilemonkeys compartimos nuestro CV de empresa con posibles candidatos en lugar de hacer copy-paste de mensajes. Te lo dejo por si tu u otros Jorges le quieren echar un ojito👀♥️

https://t.co/1g9ohAz07L

[flavia @flaviambot]

@NotionCoach For sure!! I believe that choosing the tool you’re going to work with is a strategic decision. Sometimes Notion is not the best solution!

[flavia @flaviambot]

@polrodriguezriu “comiendo cereales” o “desayuno con…”

[flavia @flaviambot]

@0x_pranjal it’s the most important thing though