The platform for service businesses to build, deploy and run agents for your clients. Faster to market and production-ready from day one.
Newcastle - London, UK
Joined April 2023
- Tweets135
- Following79
- Followers35
- Likes82
Rightbrain AI retweeted
Quick recap of evals on Rightbrain.ai
- build reference datasets from production data
- compare new versions on that historical data
- set a judge model with clear objectives and rubric
- compare results
Rightbrain AI retweeted
Built a custom AI enrichment on @attio via @RightBrainAI
New record → auto-research account → qualify against our value prop and suggest use cases with Rightbrain → enrich CRM
Next up: auto-triggering lead research at certain scores.
Rightbrain AI retweeted
Built this 'Executive Briefing Assistant' to help me deal with information overload in '26. It will:
- Accept any topic as an input, eg 'US Venezuela'
- Conduct a Perplexity Search on it
- Analyse the content from the top 10 results
- Generate an audio file with your exec brief
You can either preview an example run or 'Clone and Run' it in your own workspace on a topic of your choosing (app.rightbrain.ai/s/PSCTD). Gets even better if you tailor the prompt to your biz or industry.
Rightbrain AI retweeted
Now live on Rightbrain 🔌 Simply switch it as a primary or fallback model in your Tasks. No additional configuration needed.
Gemini 3 Flash is starting to roll out as the default model for AI Mode in Search globally.
AI Mode can now tackle your most complicated questions with greater precision — without compromising speed. ⚡
With this upgrade, AI Mode becomes an all-around more powerful tool, better at understanding your needs. You can ask more nuanced questions and it will consider each aspect to provide a thoughtful response. And as always, you’ll have access to real-time information and useful links from across the web.
Rightbrain AI retweeted
🧵 Quick demo calling a Changelog Entry Generator tool from @AnthropicAI Claude desktop via MCP (Model Context Protocol)
✨ The magic: Rightbrain's run history updates in real-time as tools execute in Claude
🎯 This means standardised, centrally-governed AI tools that work across ANY agent or assistant
Build once, deploy everywhere our team uses AI 🚀
MCP primer: lnkd.in/eFVrEmjJ
Rightbrain AI retweeted
🚀 The AI engineering inflection point is here - but most teams are still figuring out how to scale beyond "vibe coding"
While one person can now bash out a prototype in an afternoon, shipping fault-tolerant products still requires teams, processes, and discipline. The difference between success and chaos? Clear principles before the AI starts generating code.
💡 Humans own every line in production - no rubber-stamping AI output
⚖️ Automate the tedious; keep humans "on the loop" for critical decisions
📋 Standards are your AI's steering wheel - inconsistent conventions = inconsistent suggestions
🔧 Freedom at the edge, rules at the core (centralised configuration is non-negotiable)
📚 If it isn't documented, the AI won't know it
🎯 AI proficiency beats seniority - invest in everyone
Read the full guide for actionable frameworks [ 🔗 link in reply ⤵️ ]
Rightbrain AI retweeted
Pick a template, any template
1. Find a template for AI feature or tool on @RightbrainAI
2. Clone it
3. Run it
4. Tailor it
And finally deploy it with a single API call in any app, workflow or agent
Rightbrain AI retweeted
Have been following @PreSeedNow for a while as a way to track new start ups in the UK so very nice surprise to see a couple of familiar faces in my inbox today 🤩
preseednow.com/p/rightbrain ➡️ @RightbrainAI
Rightbrain AI retweeted
📽️ Just built an AI-powered interior design app with @Replit and @RightbrainAI in about 30 mins
- Define an LLM task in Rightbrain - 'analyse images of interior and provide a design brief'
- Generate an Agent Pack with structured inputs/outputs representing the task, alongside API endpoint to run it
- Drop it into Replit and watch the agent cook 🍳
- Debug, monitor, and iterate in real-time without diving into code
The result?
A clean integration between AI logic and the UI — without worrying about prompt formatting, retries, or agent drift.
Rightbrain handles LLM orchestration, monitoring, and versioning🤝 Replit makes frontend dev effortless.
Rightbrain AI retweeted
For a chance to test out how DeepSeek performs compared to your current LLM implementations or for new use cases you're looking into, drop me a DM and will hook you up with a link to test on @RightbrainAI.
Rightbrain AI retweeted
Introducing the Model Context Protocol (MCP)
An open standard we've been working on at Anthropic that solves a core challenge with LLM apps - connecting them to your data.
No more building custom integrations for every data source. MCP provides one protocol to connect them all:
Rightbrain AI retweeted
While developing @Replit Agent, we constantly face the challenge of how to interact reliably with a large number of external services.
Similarly to what Web standards enabled in the past 30 years, we need a lingua franca between AI agents and the Web ecosystem. MCP has everything it takes to become the standard that will boost Agent interoperability for the years to follow.
Rightbrain AI retweeted
🚨 Cerebras Inference is now 3x faster:
Llama3.1-70B just broke 2,100 tokens/s
- 16x faster than the fastest GPU solution
- 8x faster than GPUs running Llama *3B*
- It's like the perf of a new hardware generation in a single software release
Available now at inference.cerebras.ai
Rightbrain AI retweeted
by my calculations, the gpt4o price cut and the gemini 1.5 pro august result are "true ups" vs the Price-Intelligence Frontier of Q2 2024.
But we're now in Q3... and it's been nonstop price cuts the last 3 months since @deepseek_ai started charging $0.14/mtok for a frontier model
4o-mini and today's Gemini 1.5 Flash price cut are another order of magnitude new frontier in efficiency.
more details in @smol_ai news
[8 Aug 2024]
Too Cheap To Meter: AI prices cut 50-70% in last 30 days
Price cuts of @lmsysorg top models in the last 30 days:
- Rank 2: GPT4o cut 50% from May to Aug
- Rank 3: GPT4o-mini cut >70% vs GPT3.5/4T
- Rank 4: Llama 3.1 405b cut 46% in first 48hrs
- Rank 8: @MistralAI Large 2 cut 62% vs v1
- Rank 17: Gemini 1.5 Flash cut ~70% today (thanks @OfficialLoganK)
- Rank 17: @deepseek_ai v2 context caching cuts input token price up to 90%
(ignoring ofc their inherent quality improvements as well)
