Imagine if your Teams or Slack messages automatically turned into secure context for your AI agents — PromptQL built it

2026-03-31 · Source: VentureBeat · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cybersecurity & Data Privacy · Depth: Intermediate, medium

Summary

PromptQL, a spin-off from Hasura, has pivoted from an AI data tool to an AI-native workspace designed to transform team communications into secure, actionable context for AI agents. Launched in March 2026, the platform addresses the challenge of AI agents lacking real-time, secure data access in traditional digital workspaces like Slack or Teams, which often leads to hallucinations. PromptQL's core technology is a "Shared Wiki" that organically captures team knowledge, allowing human users to explicitly "Add to Wiki" to canonize facts. It features a virtual SQL layer for in-place data querying across various databases and SaaS tools, supports AI models like Claude Code and Cursor, and offers robust security with fine-grained access control and human-in-the-loop verification for high-stakes actions. The company employs a consumption-based pricing model using "Operational Language Units" (OLUs) and provides dedicated VPCs for enterprise customers, storing data in their S3 buckets using the Iceberg format.

Key takeaway

For CTOs and VPs of Engineering evaluating AI agent deployment, PromptQL offers a compelling solution to operationalize agentic workflows securely. Your teams can move beyond basic chatbot interactions to a system where AI agents, informed by a shared, living wiki and real-time data access, can execute complex tasks like bug fixes or CRM updates directly within communication threads. This approach reduces "coordination theater" and ensures compliance through fine-grained access control and human-in-the-loop verification, making AI agents truly actionable at enterprise scale.

Key insights

PromptQL transforms team communications into secure, actionable context for AI agents via an AI-native workspace and shared wiki.

Principles

• Context is critical for effective AI agents.
• Organic knowledge capture beats manual documentation.
• Consumption-based pricing encourages broad adoption.

Method

PromptQL captures shared context from team interactions into a human-curated wiki, queries data in-place via a virtual SQL layer, and enforces attribute-based access control with human approval for critical actions.

In practice

• Use "Add to Wiki" for explicit knowledge canonization.
• Delegate tasks to specific coding agents like Claude Code.
• Query disparate data sources with a single command.

Topics

• PromptQL
• AI-native Workspace
• Shared Wiki
• Agentic Workflows
• Virtual SQL Layer

Best for: CTO, VP of Engineering/Data, Executive, AI Engineer, MLOps Engineer, Director of AI/ML

Related on AIssential

• One person's best AI session vanishes the second they close the tab. Grab the 3 prompts that make it your team's. — Public AI interactions foster team learning and knowledge transfer by exposing operational details.
• Protestware by open source maintainer to hinder agentic coding: The jqwik 1.10.0 Prompt Injection — Open-source maintainers can embed AI prompt injections in dependencies, hidden from humans but legible to agents, posing a novel supply chain risk.
• The Agent Stack Bet — Current agent stacks create governance and reliability gaps, requiring platform-level architectural shifts for enterprise-grade autonomy.
• Stack Overflow for AI Agents — AI agent development focuses on enhancing context, memory, collaboration, and integration with developer tools.
• Introducing workspace agents in ChatGPT — Workspace agents automate complex team workflows, integrating with tools and improving through shared use.
• Mergeable by default: Building the context engine to save time and tokens — Peter Werry, Unblocked — Context engines optimize AI agent performance by providing highly relevant, curated organizational context, moving beyond simple data access.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by VentureBeat.