Datagran
@DataGran
Followers
3K
Following
785
Media
173
Statuses
745
AI knowledge and observability layer
United States
Joined February 2017
I’ve been diving deep into MCPs. It’s not new that I’ve been critical of them. My main complaint is that they constrain AI. MCPs are basically a hard-coded layer for AI, which feels counterproductive because the whole point of AI is to produce code and outputs in real time. As AI
0
1
0
Analyzing your marketing data just became easier with @Datagran. Use Claude, Replit, Cursor or any other platform that supports MCP to query your ad insights and create apps or dashboards. To start using it, just add our MCP URL which you can find on our website.
0
1
3
I believe that as the big AI frontier LLM builders like OpenAI and Google gain ground into building Superior Intelligence, it will be very hard for any company building app layers to win. Now, I think there’s a big opportunity in terms of security and gating this AI systems.
0
1
1
RT @charlesmendez: Your agents can now easily connect to Facebook ads and more to create campaigns, get insights and more! @DataGran handl…
0
1
0
Still a week to go and user growth looks good! @trydgi and experience the best data agent ever!
0
2
1
New benchmark focused on AI data agents is out, including Julius AI. Key findings: - @trydgi leads with an overall score of 0.9037, about 33% higher than the best generic model. - Almost all platforms or LLMs failed on the unstructured, tougher sessions JSON. DGi asks a
2
2
2
If you are looking for a reliable and accurate data agent to embed on your platform look no further @trydgi Have your clients ask about their spend, their performance, their orders, among many more.
0
2
1
Excited to announce the DGi Developer API. We recently shared that @trydgi is the most accurate data analyst in the market, and just this week we launched computer use. Now you can embed our agents into your organization however you want.
0
2
1
This is the most insane demo I’ve done! Personalization in marketing is hard to do at scale. Imagine creating an ad for every person with the right image and message based on that user’s behavior. Traditionally, companies don’t have the bandwidth to do this, so ad agencies
3
3
9
After weeks of focusing on making DGi the most accurate and reliable AI data analyst, we’ve been working on our next feature… One of the biggest use cases we’ve seen from our users is: “go to X page, collect the data, and process it to give me the results" Today we’re
0
2
1
New benchmark is out. It focuses only on Data Science capabilities. It also includes @grok, which is clearly making progress. Congrats to the team. @trydgi continues to lead! cc @elonmusk
About three months ago we launched DGi ( https://t.co/RbQw1Z7xML), a data agentic system. IT SUCKED, like all agentic systems do right now when it comes to data analytics. Just a few weeks ago, I used one of the big AI players to vibe code a data dashboard. A few days later, I
3
2
1
Today I’m sharing a full demo of @trydgi, the most reliable data agent on the market. In our benchmarks, DGi hallucinates 28% less than other AI agents. See the full report in my recent posts. We’re also launching data visualization in next.js apps with beautiful components.
1
2
18
@charlesmendez I’ve been pretty shocked at how well this AI stack has improved a project I’ve been doing. I’ve made more progress in making use of my data in two afternoons, than I had in two weeks. Very very cool.
0
3
1
The best way to improve is by talking to customers! I do it every chance I get. @trydgi truly excels at data.
0
2
1
Shipping Friday!! Back in 2012, I built one of the top 20 ad agencies. How? By getting the right context. I used my MBA and creative background to bring together two worlds that agencies usually kept apart. That led to a concept we called Business Creativity. For the first time,
+1 for "context engineering" over "prompt engineering". People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window
0
2
1
We recently launched DGi (@DG_intel), an AI data agent. We knew it wasn’t perfect, but launched anyway. After years of building products, I’ve learned that the most important thing is retention. It’s great to see how retention spikes as we improve the product. v2 agents soon!
1
3
0
We just launched the Metadata Store in DGi (@DG_intel) Until now, you could save connections, but there was no place to view them or tell the AI which one to use. That changes today. The new Metadata Store lets you manage your connections and instruct the AI to use your
0
2
4