@drantunes

PhD in Computer Science πŸŽ“ Teaching thousands devs since 2009. https://xitter.cf/t.co/crFXTOOt5p πŸ€– Today, researching and using AI, Agents and Agentic Workflows

 Brazil
linkedin.com/in/drantunes
Joined March 2009
  • Tweets3.1K
  • Following592
  • Followers537
171Media
Diego R. Antunes retweeted
Sam Bhagwat
@calcsam2h
We just launched an insurance policy checking @mastra agent template:
1
2
1
18
1,545
Diego R. Antunes retweeted
Sam Bhagwat
@calcsam2h
Replying to @calcsam @drantunes
And here's the template page: mastra.ai/templates/insuranc…

Insurance Policy Checking | Mastra Templates

Compares insurance proposals and policies, flags discrepancies, and generates reports

mastra.ai
1
4
184
Diego R. Antunes retweeted
Alex Booker
@bookercodes9h
Do you have an agent you want to build for your team? I'm doing a hands-on Mastra intro on Thursday - from TypeScript to a deployed agent in Slack. Join me (and bring ideas!) luma.com/mastra-88zp

Build, Deploy, Observe TypeScript Agents on Mastra Β· Luma

You probably have a list of agents you’d like to build. A new product. A better customer experience. A way to free your team from repetitive work. The harder…

luma.com
1
2
10
473
Diego R. Antunes retweeted
Mastra
@mastraOct 26
New template: Lead qualification Build a Mastra workflow that takes leads from JSON API or Attio CRM and checks them against your ICP.
2
3
23
2,281
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 26
Today we're announcing an early access program for Mastra Knowledge! At Mastra we build lots of internal Slack agents. But when we built our first company knowledge graph, it vastly improved agent quality. Grab time here to pilot with our team: calendly.com/mastra-team/mas…

Mastra Knowledge - Mastra Team

calendly.com
6
11
6
88
7,605
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 22
Most LLMs get "context rot": recall decreases as context window approaches the context limit. We wondered: do the new "System 1" decision models get context rot? So we tested Jev, Clef, and Luna Decisions across 400 questions. Turns out decision models get context rot, too.
21
8
39
2,729
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 20
We’ve worked with hundreds of teams shipping Mastra agents into production. Now, it's your turn. We're introducing Mastra Launch and offering hands-on FDE support to get your agent live within 90 days. Let's chat: calendly.com/mastra-team/lau…

Mastra Launch - Mastra Team

calendly.com
16
15
6
66
5,591
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 14
Today we're excited to launch trace imports! Export traces from Langfuse to the Mastra platform:
11
3
1
50
3,092
Diego R. Antunes retweeted
Alex Booker
@bookercodesOct 14
Join Charlie and I tomorrow for a workshop on how to build a company brain with Mastra Connect! You'll learn to: - Connect an agent to your knowledge bases - Give it tools to look things up and take action - Put it in your team's Slack πŸš€ luma.com/mastra-304z

Build a Company Brain with Mastra Connect Β· Luma

Your team’s work lives in Notion, Linear, Slack, and other workspace apps. Giving agents access to those tools has meant building integrations yourself or…

luma.com
2
5
391
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 13
Today we're excited to launch metrics API! Query agent costs, latency, and errors, then use the data in your reports / apps:
23
6
3
64
4,127
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 12
Incredibly stoked to launch Thread View for traces in the Mastra studio. Zoom in to see a single chat turn and its associated span. Zoom out to see the whole conversation and underlying trace:
10
8
6
70
7,571
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 8
Over the last year, we've met some incredible folks building agents for clients. So today, we're launching the Mastra agency program: A small list of agencies certified by our FDEs, with a direct line to us and visibility into our roadmap. mastra.ai/blog/mastra-agency…

Introducing the Mastra Agency Program | Mastra Blog

A network of certified agencies and consultancies that build Mastra agents for their clients, plus our five launch partners.

mastra.ai
6
10
5
69
9,247
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 6
Workflow + agent schedules are now GA! Since we launched the July beta we: - simplified running schedules on serverless / multi-server setups - added the ability to declare a cron schedule in an agent's file
Sam Bhagwat
@calcsamJul 8
Today we're introducing Schedules for Mastra agents and workflows. Wake up your agent every minute, every hour, every day, or any cadence with a `cron` key:
2
1
1
22
2,625
Diego R. Antunes retweeted
Mastra
@mastraOct 6
We shipped a new template for monitoring competitor pages. A page edit doesn't always mean an important update. Use Jev to evaluate each change, and decide if it matters to you. mastra.ai/templates/competit…

Competitor Monitor with Jev | Mastra Templates

Monitor competitor pages with Mastra and Jev, classifying changes with supporting evidence

mastra.ai
3
2
15
1,414
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamOct 5
We're excited to launch agent signals in GA today! Since our June alpha, we added: - canceling queued messages - one-off "transient" signals - ordering guarantees
Tyler Barnes
@tylbarJun 3
🚨We shipped a new context engineering primitive @mastra today, Agent Signals! (alpha) πŸ”“Unlocks: multiplayer steering, dynamic cacheable system prompts, agent notifications (gh/email/etc), and automatic behavior guidance 🧡
2
6
1
36
4,235
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamSep 30
Build agents Make money
Neon
@neondatabaseSep 30
Build Personal Agents Hack Β· Sun, Oct 4 Β· San Francisco Total prize pool: $279,500 + $1,625 in credits for every hacker RSVP: luma.com/build-agents
2
17
2,222
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamSep 30
Today we shipped our #1 feature request for Mastra Factory: it now connects to Jira, GitLab and Incident.io Connect your backlog and start churning through tickets:
10
10
5
76
9,428
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamSep 29
We have an intuitive understanding of how auth for humans works. But what about auth for agents? On Thursday, @bookercodes is walking through things like resource-level permission checks, multi-tenant access, and fine-grained context for agents: luma.com/mastra-xy3o

Build Secure Agents with Auth and FGA Β· Luma

Building agent apps for real users quickly creates a familiar challenge: authentication is only the first step. Once your app serves multiple teams,…

luma.com
2
3
5
799
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamSep 29
Here's the blog post: mastra.ai/blog/introducing-m…

Introducing Memory Hooks | Mastra Blog

Monitor your agent's memory cycle, or intercept what it sees and stores.

mastra.ai
1
1
3
291
Diego R. Antunes retweeted
Sam Bhagwat
@calcsamSep 29
Today we're launching memory hooks! Lifecycle hooks (πš˜πš—π™Ύπš‹πšœπšŽπš›πšŸπšŠπšπš’πš˜πš—πš‚πšπšŠπš›πš, πš˜πš—πšπšŽπšπš•πšŽπšŒπšπš’πš˜πš—π™΄πš—πš, etc) to trigger external events Transform hooks (πš‹πšŽπšπš˜πš›πšŽπ™Ύπš‹πšœπšŽπš›πšŸπšŠπšπš’πš˜πš—, πšŠπšπšπšŽπš›πšπšŽπšπš•πšŽπšŒπšπš’πš˜πš—, etc) to alter how memory is stored:
5
10
1
32
3,406
Load more