Daniel Davis
@trustspooky.bsky.social
http://trustgraph.ai | Knowledge Graphs for AI | Using AI to convert knowledge to intelligence
LLMs are slow readers... 📖 🦥 🤔
It's such a simple idea, but yet, I haven't seen anyone else talking about it. LLMs are slow readers - on computer timescales.
Check out all of this an more on the latest episode 👇
Engineering Thoughts: youtu.be/yAb1Db4AfW0
It's such a simple idea, but yet, I haven't seen anyone else talking about it. LLMs are slow readers - on computer timescales.
Check out all of this an more on the latest episode 👇
Engineering Thoughts: youtu.be/yAb1Db4AfW0
LLMs Are Slow Readers | Part 4 | Engineering Thoughts | TrustGraph
YouTube video by TrustGraph
youtu.be
November 12, 2025 at 5:18 PM
LLMs are slow readers... 📖 🦥 🤔
It's such a simple idea, but yet, I haven't seen anyone else talking about it. LLMs are slow readers - on computer timescales.
Check out all of this an more on the latest episode 👇
Engineering Thoughts: youtu.be/yAb1Db4AfW0
It's such a simple idea, but yet, I haven't seen anyone else talking about it. LLMs are slow readers - on computer timescales.
Check out all of this an more on the latest episode 👇
Engineering Thoughts: youtu.be/yAb1Db4AfW0
It’s the 🚨 1 hour warning 🚨 for our latest webinar with Ishtiaque Mohammad from SowFin and our own Robert Hamilton! Tune in for a great discussion on how SowFin are using @trustgraph.bsky.social to improve agentic solutions for corporate FP&A and M&A.
youtu.be/0-4d442q9j4
youtu.be/0-4d442q9j4
Agentic AI for Corporate Finance with SowFin | AI Fireside Chat | TrustGraph
YouTube video by TrustGraph
youtu.be
November 5, 2025 at 6:09 PM
It’s the 🚨 1 hour warning 🚨 for our latest webinar with Ishtiaque Mohammad from SowFin and our own Robert Hamilton! Tune in for a great discussion on how SowFin are using @trustgraph.bsky.social to improve agentic solutions for corporate FP&A and M&A.
youtu.be/0-4d442q9j4
youtu.be/0-4d442q9j4
Now with support for @ovhcloudus.bsky.social!
Announcing the release of version 1.2! 👏 🚀
The highlights:
🚀 AI Agent-Powered Knowledge Extraction
🚀 Structured Data Handling (MVP)
🚀 Expanded LLM and Cloud Support
🚀 New Developer and Operator Tooling
🚀 Enhanced Stability and Modernization
trustgraph.ai/press-releas...
The highlights:
🚀 AI Agent-Powered Knowledge Extraction
🚀 Structured Data Handling (MVP)
🚀 Expanded LLM and Cloud Support
🚀 New Developer and Operator Tooling
🚀 Enhanced Stability and Modernization
trustgraph.ai/press-releas...
Introducing Agents for Knowledge Graph Construction and Expanded Enterprise Data Support - TrustGraph - The Sovereign Universal AI Adapter
Take control of your data and build your AI future with TrustGraph. Deploy LLMs and graph driven intelligence in any environment enabling data sovereignty and full control over the software stack.
trustgraph.ai
August 22, 2025 at 7:39 PM
Now with support for @ovhcloudus.bsky.social!
Thrilled to announce MCP in @trustgraph.bsky.social! This has been a release that has really excited the team. So much potential for combining the power of GraphRAG with MCP interoperability!
www.youtube.com/watch?v=A_hR...
www.youtube.com/watch?v=A_hR...
MCP Integration and New Agent Tools | TrustGraph
YouTube video by TrustGraph
www.youtube.com
July 17, 2025 at 4:17 PM
Thrilled to announce MCP in @trustgraph.bsky.social! This has been a release that has really excited the team. So much potential for combining the power of GraphRAG with MCP interoperability!
www.youtube.com/watch?v=A_hR...
www.youtube.com/watch?v=A_hR...
Thanks @chrismdp.com for including @trustgraph.bsky.social in his recent discussion on GraphRAG! 🙏
www.chrismdp.com/graph-rag/
www.chrismdp.com/graph-rag/
Why Graph RAG is the Future
Standard RAG is like reading a book one sentence at a time, out of order. We need something new.
When you read a book, you do not jump randomly between paragraphs, hoping to piece together the story....
www.chrismdp.com
May 27, 2025 at 3:49 PM
Thanks @chrismdp.com for including @trustgraph.bsky.social in his recent discussion on GraphRAG! 🙏
www.chrismdp.com/graph-rag/
www.chrismdp.com/graph-rag/
Pitch Battle Alert ⚔️ 🚨
@trustgraph.bsky.social was selected as a finalist for the #SaaStr Showdown on May 14th! 🎉 Come check out all the pitches in a rapid fire pitch battle, and hear about all the features coming in TrustGraph!
Register here: lu.ma/efrd9afv
@trustgraph.bsky.social was selected as a finalist for the #SaaStr Showdown on May 14th! 🎉 Come check out all the pitches in a rapid fire pitch battle, and hear about all the features coming in TrustGraph!
Register here: lu.ma/efrd9afv
SaaStr Showdown: The Ultimate B2B SaaS Pitch Battle & Mixer · Luma
Join us for an exclusive offsite event during SaaStr!
SaaStr Showdown is where 10 top B2B SaaS startups go head-to-head in an epic VC-judged pitch battle,…
lu.ma
May 9, 2025 at 6:51 PM
Pitch Battle Alert ⚔️ 🚨
@trustgraph.bsky.social was selected as a finalist for the #SaaStr Showdown on May 14th! 🎉 Come check out all the pitches in a rapid fire pitch battle, and hear about all the features coming in TrustGraph!
Register here: lu.ma/efrd9afv
@trustgraph.bsky.social was selected as a finalist for the #SaaStr Showdown on May 14th! 🎉 Come check out all the pitches in a rapid fire pitch battle, and hear about all the features coming in TrustGraph!
Register here: lu.ma/efrd9afv
Is your AI strategy aligned with Knowledge Sovereignty? 🤔
Learn how @trustgraph.bsky.social empowers you to:
✅ Deploy AI anywhere (on-prem, regional cloud)
✅ Govern your own AI-generated Knowledge Cores
✅ Maintain control over valuable insights
blog.trustgraph.ai/p/reclaiming...
Learn how @trustgraph.bsky.social empowers you to:
✅ Deploy AI anywhere (on-prem, regional cloud)
✅ Govern your own AI-generated Knowledge Cores
✅ Maintain control over valuable insights
blog.trustgraph.ai/p/reclaiming...
Reclaiming Knowledge Sovereignty in the Age of AI
Empower your enterprise with AI, without sacrificing an ounce of control. Provision your path to Knowledge Sovereignty with TrustGraph.
blog.trustgraph.ai
May 6, 2025 at 10:36 PM
Is your AI strategy aligned with Knowledge Sovereignty? 🤔
Learn how @trustgraph.bsky.social empowers you to:
✅ Deploy AI anywhere (on-prem, regional cloud)
✅ Govern your own AI-generated Knowledge Cores
✅ Maintain control over valuable insights
blog.trustgraph.ai/p/reclaiming...
Learn how @trustgraph.bsky.social empowers you to:
✅ Deploy AI anywhere (on-prem, regional cloud)
✅ Govern your own AI-generated Knowledge Cores
✅ Maintain control over valuable insights
blog.trustgraph.ai/p/reclaiming...
Is your AI stuck in a Memento loop? 🔁 Retrieving fragments but lacking true knowledge leads to hallucinations, just like Leonard's notes misled him.
❌ Fragmented recall = AI Amnesia
✅ Knowledge Cores = Real Understanding
blog.trustgraph.ai/p/how-trustg...
❌ Fragmented recall = AI Amnesia
✅ Knowledge Cores = Real Understanding
blog.trustgraph.ai/p/how-trustg...
Part 3: How TrustGraph's Knowledge Cores End the Memento Nightmare
Giving AI Its Knowledge Back
blog.trustgraph.ai
April 28, 2025 at 4:38 PM
Is your AI stuck in a Memento loop? 🔁 Retrieving fragments but lacking true knowledge leads to hallucinations, just like Leonard's notes misled him.
❌ Fragmented recall = AI Amnesia
✅ Knowledge Cores = Real Understanding
blog.trustgraph.ai/p/how-trustg...
❌ Fragmented recall = AI Amnesia
✅ Knowledge Cores = Real Understanding
blog.trustgraph.ai/p/how-trustg...
What's the difference between memory and knowledge, and why does it matter for AI agents?
blog.trustgraph.ai/p/why-your-a...
blog.trustgraph.ai/p/why-your-a...
Part 2: Why Your AI is Stuck in a Memento Loop
If we want AI to escape this loop, we need to fundamentally change how we provide information. We need to move beyond retrieving isolated Polaroids and start building systems that can understand the w...
blog.trustgraph.ai
April 26, 2025 at 10:26 PM
What's the difference between memory and knowledge, and why does it matter for AI agents?
blog.trustgraph.ai/p/why-your-a...
blog.trustgraph.ai/p/why-your-a...
Is "memory" even what AI systems need? 🤔
It didn't work out so well for Leonard in Memento...
blog.trustgraph.ai/p/the-mement...
It didn't work out so well for Leonard in Memento...
blog.trustgraph.ai/p/the-mement...
Part 1: The Memento Problem with AI Memory
We need to stop celebrating glorified search indices as "memory" and start demanding systems capable of building actual knowledge. Until then, we're just building better mimics, doomed to repeat the m...
blog.trustgraph.ai
April 25, 2025 at 9:52 PM
Is "memory" even what AI systems need? 🤔
It didn't work out so well for Leonard in Memento...
blog.trustgraph.ai/p/the-mement...
It didn't work out so well for Leonard in Memento...
blog.trustgraph.ai/p/the-mement...
The future of AI is not in monolithic LLMs. It's in a highly orchestrated symphony of systemic software. 🎻 blog.trustgraph.ai/p/the-sympho...
The Symphony of the AI System
This isn't just theory. Platforms like TrustGraph are pioneering this Synaptic Automation System approach proving the future of AI is in systems and not LLM monoliths.
blog.trustgraph.ai
April 14, 2025 at 6:06 PM
The future of AI is not in monolithic LLMs. It's in a highly orchestrated symphony of systemic software. 🎻 blog.trustgraph.ai/p/the-sympho...
It's funny how quickly LLM model versions have slowed down. 🐢
Just last year, whole number versions released every few months. What have been some recent releases (not counting Llama 4)?
- GPT-4.1
- Gemini 2.5
- Claude 3.7
What's going to be the next OpenAI release? GPT-4.2? Then GPT-4.21?
Just last year, whole number versions released every few months. What have been some recent releases (not counting Llama 4)?
- GPT-4.1
- Gemini 2.5
- Claude 3.7
What's going to be the next OpenAI release? GPT-4.2? Then GPT-4.21?
April 14, 2025 at 5:33 PM
It's funny how quickly LLM model versions have slowed down. 🐢
Just last year, whole number versions released every few months. What have been some recent releases (not counting Llama 4)?
- GPT-4.1
- Gemini 2.5
- Claude 3.7
What's going to be the next OpenAI release? GPT-4.2? Then GPT-4.21?
Just last year, whole number versions released every few months. What have been some recent releases (not counting Llama 4)?
- GPT-4.1
- Gemini 2.5
- Claude 3.7
What's going to be the next OpenAI release? GPT-4.2? Then GPT-4.21?
How can we solve the demo-to-production problem with agents? 🤔
Autonomous Knowledge Operations. 💥
blog.trustgraph.ai/p/autonomous...
Autonomous Knowledge Operations. 💥
blog.trustgraph.ai/p/autonomous...
Stop Thinking AI Agents, Start Engineering Autonomous Knowledge Operations
Discover how autonomous knowledge operations transcend traditional AI agents, solving the critical demo-to-production challenge with continuous, reliable system design.
blog.trustgraph.ai
April 10, 2025 at 1:01 AM
How can we solve the demo-to-production problem with agents? 🤔
Autonomous Knowledge Operations. 💥
blog.trustgraph.ai/p/autonomous...
Autonomous Knowledge Operations. 💥
blog.trustgraph.ai/p/autonomous...
Building Trust in Agentic Systems 🤝
Taken from my talk this past Thursday at @cloudflare.social HQ in SF. Special thanks to @qdrant.bsky.social and @groq.com for supporting the event! www.youtube.com/watch?v=E0bG...
Taken from my talk this past Thursday at @cloudflare.social HQ in SF. Special thanks to @qdrant.bsky.social and @groq.com for supporting the event! www.youtube.com/watch?v=E0bG...
Building Trust in Agentic Systems
YouTube video by Our Agentic Future
www.youtube.com
March 29, 2025 at 5:23 PM
Building Trust in Agentic Systems 🤝
Taken from my talk this past Thursday at @cloudflare.social HQ in SF. Special thanks to @qdrant.bsky.social and @groq.com for supporting the event! www.youtube.com/watch?v=E0bG...
Taken from my talk this past Thursday at @cloudflare.social HQ in SF. Special thanks to @qdrant.bsky.social and @groq.com for supporting the event! www.youtube.com/watch?v=E0bG...
Reposted by Daniel Davis
Our biggest set of features EVER are now available in release 0.21.17! 🚀 Support for @mistralai.bsky.social, @lmstudio-ai.bsky.social, Azure, and AWS are just a teaser of all the capabilities now available in TrustGraph! github.com/trustgraph-a...
GitHub - trustgraph-ai/trustgraph: Connect your AI app directly to your data with a full stack solution. Fully connected Agentic Graph RAG pipelines mean you can focus on fine tuning your app and not ...
Connect your AI app directly to your data with a full stack solution. Fully connected Agentic Graph RAG pipelines mean you can focus on fine tuning your app and not building data infrastructure. - ...
github.com
March 25, 2025 at 9:17 PM
Our biggest set of features EVER are now available in release 0.21.17! 🚀 Support for @mistralai.bsky.social, @lmstudio-ai.bsky.social, Azure, and AWS are just a teaser of all the capabilities now available in TrustGraph! github.com/trustgraph-a...
Yes, you still need vector embeddings for Graph RAG❕ 🤔
Why rely on complex ontologies and LLMs to generate queries when you can map embeddings to the graph?
Thanks to @qdrant.bsky.social for giving me the opportunity to present @trustgraph.bsky.social to the community!
youtu.be/20YAskR1SGs
Why rely on complex ontologies and LLMs to generate queries when you can map embeddings to the graph?
Thanks to @qdrant.bsky.social for giving me the opportunity to present @trustgraph.bsky.social to the community!
youtu.be/20YAskR1SGs
Why You Still Need Vector Embeddings in Graph RAG | TrustGraph
YouTube video by TrustGraph
youtu.be
March 11, 2025 at 10:23 PM
Yes, you still need vector embeddings for Graph RAG❕ 🤔
Why rely on complex ontologies and LLMs to generate queries when you can map embeddings to the graph?
Thanks to @qdrant.bsky.social for giving me the opportunity to present @trustgraph.bsky.social to the community!
youtu.be/20YAskR1SGs
Why rely on complex ontologies and LLMs to generate queries when you can map embeddings to the graph?
Thanks to @qdrant.bsky.social for giving me the opportunity to present @trustgraph.bsky.social to the community!
youtu.be/20YAskR1SGs
With so much talk about MCP lately, I started looking into it again. Things it doesn't do:
- Deployment management
- Data management
- Compute resource management
- Data security management
What problem is it actually solving? Am I missing something???
- Deployment management
- Data management
- Compute resource management
- Data security management
What problem is it actually solving? Am I missing something???
March 6, 2025 at 12:02 AM
With so much talk about MCP lately, I started looking into it again. Things it doesn't do:
- Deployment management
- Data management
- Compute resource management
- Data security management
What problem is it actually solving? Am I missing something???
- Deployment management
- Data management
- Compute resource management
- Data security management
What problem is it actually solving? Am I missing something???
Vibecoding and Knowledge Layers for Agents 😎
Thanks to @convex.dev and @waynesutton.bsky.social
for giving me the opportunity last night to talk about
@trustgraph.bsky.social and knowledge layers for agents. #Vibecode
www.youtube.com/watch?v=R9Dq...
Thanks to @convex.dev and @waynesutton.bsky.social
for giving me the opportunity last night to talk about
@trustgraph.bsky.social and knowledge layers for agents. #Vibecode
www.youtube.com/watch?v=R9Dq...
AI Code Gen + Full Stack Demo Night @Convex
YouTube video by Convex
www.youtube.com
February 28, 2025 at 5:18 PM
Vibecoding and Knowledge Layers for Agents 😎
Thanks to @convex.dev and @waynesutton.bsky.social
for giving me the opportunity last night to talk about
@trustgraph.bsky.social and knowledge layers for agents. #Vibecode
www.youtube.com/watch?v=R9Dq...
Thanks to @convex.dev and @waynesutton.bsky.social
for giving me the opportunity last night to talk about
@trustgraph.bsky.social and knowledge layers for agents. #Vibecode
www.youtube.com/watch?v=R9Dq...
Thanks to everyone that attended our Agentic Graph RAG workshop this past Monday at the AWS Lofts with @trustgraph.bsky.social and Memgraph!
It was great to meet so many people with a genuine interest in knowledge graphs, AI, and the complexities of human communication!
It was great to meet so many people with a genuine interest in knowledge graphs, AI, and the complexities of human communication!
February 26, 2025 at 4:41 PM
Thanks to everyone that attended our Agentic Graph RAG workshop this past Monday at the AWS Lofts with @trustgraph.bsky.social and Memgraph!
It was great to meet so many people with a genuine interest in knowledge graphs, AI, and the complexities of human communication!
It was great to meet so many people with a genuine interest in knowledge graphs, AI, and the complexities of human communication!
Thanks to @nicolay.fyi for giving me the opportunity to talk about @trustgraph.bsky.social on How AI Is Built!
Labels such as "facts", "observations", and "assertions" take on new meanings when we begin to consider time. Click 👇 to watch the full episode! 🎙️
youtu.be/VpFVAE3L1nk?
Labels such as "facts", "observations", and "assertions" take on new meanings when we begin to consider time. Click 👇 to watch the full episode! 🎙️
youtu.be/VpFVAE3L1nk?
Temporal RAG: Embracing Time for Smarter, Reliable Knowledge Graphs
YouTube video by How AI Is Built
youtu.be
February 17, 2025 at 6:36 PM
Thanks to @nicolay.fyi for giving me the opportunity to talk about @trustgraph.bsky.social on How AI Is Built!
Labels such as "facts", "observations", and "assertions" take on new meanings when we begin to consider time. Click 👇 to watch the full episode! 🎙️
youtu.be/VpFVAE3L1nk?
Labels such as "facts", "observations", and "assertions" take on new meanings when we begin to consider time. Click 👇 to watch the full episode! 🎙️
youtu.be/VpFVAE3L1nk?
Reading @anthropic.com's new paper on Constitutional Classifiers and AI safety, I can't help but wonder why no one discussing AI safety ever mentions DoCRA? Isn't "Due Care" and "Duty of Care" really the concepts of interest for an AI provider? docra.org/standard/
The DoCRA Standard – DOCRA
1.0 To provide to the public a risk analysis method that aligns with judicial and regulatory expectations for demonstrating “due care,” the “reasonable person,” and “reasonable,” and “appropriate” safeguards.
docra.org
February 3, 2025 at 5:38 PM
Reading @anthropic.com's new paper on Constitutional Classifiers and AI safety, I can't help but wonder why no one discussing AI safety ever mentions DoCRA? Isn't "Due Care" and "Duty of Care" really the concepts of interest for an AI provider? docra.org/standard/
Yes, you still need RAG.
Sure, DeepSeek-R1 is impressive, but what happens when you ask it an obscure question? Should we be surprised it struggles with obscure knowledge?
Sure, DeepSeek-R1 is impressive, but what happens when you ask it an obscure question? Should we be surprised it struggles with obscure knowledge?
Yes, You Still Need RAG
It doesn't matter how good DeepSeek-R1 is, you still need RAG. Are you trying to understand an obscure topic that is highly complex and unique? Yep, still need RAG.
blog.trustgraph.ai
January 28, 2025 at 7:31 PM
Yes, you still need RAG.
Sure, DeepSeek-R1 is impressive, but what happens when you ask it an obscure question? Should we be surprised it struggles with obscure knowledge?
Sure, DeepSeek-R1 is impressive, but what happens when you ask it an obscure question? Should we be surprised it struggles with obscure knowledge?
Reposted by Daniel Davis
🚀 v0.19.19 is now live! 🚀
✅ Dual Model Mode!
✅ 3D Graph Visualization!
✅ BIG reliability improvements!
✅ Dual Model Mode!
✅ 3D Graph Visualization!
✅ BIG reliability improvements!
GitHub - trustgraph-ai/trustgraph: Explore Your Data in 3D with Agentic Knowledge Discovery to See Your Data in a New Light 🌞
Explore Your Data in 3D with Agentic Knowledge Discovery to See Your Data in a New Light 🌞 - trustgraph-ai/trustgraph
github.com
January 13, 2025 at 7:02 PM
🚀 v0.19.19 is now live! 🚀
✅ Dual Model Mode!
✅ 3D Graph Visualization!
✅ BIG reliability improvements!
✅ Dual Model Mode!
✅ 3D Graph Visualization!
✅ BIG reliability improvements!
Bored with the typical 2D graph visualizations? Tired of having to click through a sea of bubbles to see your data? Try the new 3D visualizer in TrustGraph!
Explore you data in a whole new way with the Data Workbench! 🕵️ Click and drag, expand topics, and visualize the directionality of relationships. No Cypher or GQL queries required! Fully automated graph building with AI chat.
January 6, 2025 at 10:11 PM
Bored with the typical 2D graph visualizations? Tired of having to click through a sea of bubbles to see your data? Try the new 3D visualizer in TrustGraph!