DGi
@trydgi
Followers
244
Following
0
Media
4
Statuses
37
The AI data agent for developers.
Miami, FL
Joined March 2025
If you now understand how a company like @FactoryAI can create the best coding agent, you can understand how @trydgi created the best data analysis agent.
How did a team of 4 research engineers beat $100B labs like OpenAI and Anthropic in establishing the best coding agent? It starts with having a killer engineer on your team. In our case, we have @_AbhaySinghal 🧵
0
1
5
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
We are getting more than expected usage and our platform was down almost all morning. The issue has been resolved.
0
0
2
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
By popular demand, we’re launching FastMode for chat. If you want to quickly ask the AI about your ongoing conversation with the agents for faster analysis, just enable FastMode in the chat text box. If you open the IDE it will switch to code editing FastMode.
0
1
0
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
In just 2 weeks, we’ve shipped: •Fast Mode to quickly edit code in the IDE •Deep Understanding to instantly research your repo and web links •Checkpoints to roll back your conversation when needed
0
0
2
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
.@trydgi is my new Airflow. I fetched data from Finnhub to get S&P tickers, uploaded them to my database, then created a script that processes the data, calculates a RoRo, and sends it to Slack every day. All vibe-coded. Benefits over Replit: - Easy access to environment
0
1
0
Scheduling is here 📆 Run your workflows automatically. Daily reports, data syncs, whatever you need. Set it once and let it run.
0
1
0