Heka

The description states:

• Heka is described as “Cursor for GIS” — a tool enabling natural language spatial problem-solving.
• It allows users to ask questions like “Where should Calgary build its next hospital?” and returns explainable maps and analysis.
• It uses GPT-5.6 for planning, but does not perform GIS analysis itself; instead, it discovers datasets, validates evidence, and executes deterministic GIS workflows using PyQGIS and public data.
• The system visualizes results on an interactive globe built with CesiumJS.
• It supports both a web demo and a desktop IDE, built with React, Tauri, TypeScript, and Cloudflare Workers.

Inference Heka appears to be a hybrid AI-GIS tool that separates AI intent understanding from GIS computation, aiming for explainability and data integrity over hallucination.

The description states:

• Heka positions itself as a way to “ask Earth in natural language” to understand spatial feasibility.
• It claims to be a “Cursor for GIS,” implying it makes GIS more accessible like how Cursor made coding easier.
• The author emphasizes that Heka does not fabricate answers when data is lacking — it admits limitations.
• It aims to make spatial reasoning as natural as writing code became with AI.

Inference The positioning evolves from a hackathon prototype to a vision of democratizing GIS through AI, but no evidence suggests this has moved beyond the experimental stage.

The description states:

• Heka is intended for users who ask spatial questions — e.g., urban planners, environmental scientists, disaster response teams, infrastructure engineers.
• It targets those who would otherwise need to learn GIS software or hunt for datasets manually.

Inference The ICP likely includes professionals working in environmental planning, transportation, conservation, and climate resilience sectors, but no evidence of customer interviews, usage data, or personas is provided.

The description states:

• No pricing model or monetization strategy is mentioned.
• The project was built as a hackathon submission with no commercial deployment or revenue sources described.

Inference There is no evidence of any business model or pricing structure, and the tool appears to be in early prototype form.

The description states:

• Built using React, TypeScript, Tauri, CesiumJS, PyQGIS, Cloudflare Workers, and GPT-5.6.
• The AI does not perform GIS analysis directly; it plans the workflow, then deterministic GIS tools execute.
• It integrates with open datasets and supports explainable outputs (layers, ranked candidates, maps).
• It was built in two days during a hackathon.

Inference The architecture shows a deliberate separation of AI planning from GIS execution, which is technically sound but unproven at scale. The short development time suggests early-stage experimentation.

The description states:

• Heka was built in 2 days during a hackathon.
• It has a hosted web demo and a desktop IDE.
• It supports real QGIS processing pipelines on public datasets.
• It can admit when data is insufficient, rather than hallucinate.

Inference There is no evidence of user adoption, revenue, or product-market fit beyond the prototype stage. The tool is described as functional but not yet deployed for real-world use.

The description states:

• No direct competitors are named.
• It positions itself as a “Cursor for GIS,” implying a comparison to AI coding tools like Cursor.
• It leverages open-source GIS tools (QGIS, PyQGIS) and spatial data platforms (OpenStreetMap, GeoJSON).

Inference The competitive landscape includes traditional GIS software (e.g., QGIS, ArcGIS), AI-powered analytics platforms, and geospatial data marketplaces. However, no evidence of competitive analysis or differentiation is provided.

The description states:

• The tool was built in 2 days — a strong signal of early-stage development.
• It uses GPT-5.6, which may not be available to all users or scalable for enterprise use.
• It relies on open datasets and public GIS tools — potentially limiting its utility for proprietary or complex spatial problems.

1. What specific spatial problems are you solving, and who are your early adopters?
2. How do you plan to scale beyond the current prototype and open datasets?
3. What is your roadmap for integrating proprietary data sources or enterprise GIS tools?
4. Do you have any early user feedback or pilot programs?
5. What is your long-term vision for monetization, and how does it align with your current product direction?