Blocktrace builds AI Chatbot to simplify blockchain transaction tracking

Scanning and analyzing a blockchain can be challenging, especially when sorting through tens of thousands of blockchain addresses and millions of transactions. It is tedious and time-consuming, and the story being told is often elusive. Austin-based startup Blocktrace hopes that artificial intelligence can speed up the blockchain analysis process, and uncover trends and anomalies more easily.

Launched in 2018 by software engineer Shaun MaGruder, whose background includes working as head of training at blockchain forensics firm Chainalysis, Blocktrace is an AI-fortified blockchain forensics and analytics service provider. Using a chatbot they called Robby the Robot – after the iconic character from the TV series Forbidden Planet – Blocktrace developed its AI to interact with data on the Bitcoin blockchain.

Blocktrace CEO MaGruder told Decrypt in an interview that the company decided to start the Robby project with Bitcoin because of its large sample size and history.

“Bitcoin is a great project to start with and will probably always be around, just like Ethereum,” MaGruder said. “It is considered OG because it was the first and has a large selection of user base addresses with a lot of activity.”

According to MaGruder, a copy of the Bitcoin blockchain data is stored in Blocktrace’s database – already a significant technical feat. Enhanced with an AI layer, their application allows users to ask natural language questions like a virtual assistant.

A natural language model is a type of artificial intelligence designed to understand and process human language, similar to how humans do.

“Users can quickly request specific information, such as transactions between dates and amounts,” MaGruder said. “This saves time compared to the manual process, which can take one to two hours using a blockchain explorer.”

MaGruder explains that Blocktrace aims to enable investigators and users to use the technology developed by OpenAI to quickly find Bitcoin addresses and identify transactions that occurred on the network with greater accuracy and detail.

“Instead of requiring a data engineer or data scientist to translate natural language queries into SQL queries, Robbie has already been trained in the data model and can quickly retrieve results for the user,” MaGruder said, calling the process more efficient and one that does. does not require continuous training for new data scientists.

While still in beta, Robby is expected to be made available to the public later this year. However, before Robby rolls out to the public, MaGruder said the chatbot would first be given to a closed group to test.

“We want to make sure that Robbie is stable and that we don’t fall flat on our faces when we release it to the public,” MaGruder said. “We want to make sure that the questions that the audience is going to ask are questions that we’ve already asked Robbie.”

“As expected, people will compare Robbie to a traditional blockchain explorer and determine whether Robbie is right or wrong,” MaGruder said. “To gather feedback, we will implement a thumbs up and thumbs down button. A thumbs up will serve as positive reinforcement, while a thumbs down will indicate areas that need improvement.”

Blocktrace is just the latest Web3 company looking to harness the power of artificial intelligence for blockchain analysis. Others using the technology include Elliptic, Chainalysis, CipherTrace and Nansen.

“It’s something we’re looking at very deeply,” said Andrew Thurman, a Nansen engineer. Decrypt at ETH Denver. “You can use things like AI analytics on the blockchain to see if [wallets] doing the same things at the same time.” Thurman added that while there are no explicit connections, you can assume with a good level of confidence that all of these wallets are linked to the same device.

“Algorithmic tagging and AI tagging I think has a pretty significant future in blockchain analytics,” Thurman said.