Steltic

// Explainer

Steltic explainer — what it is and how a design run works

// Hot-rolled steel — AISC 360/341

Structural steel buildings (currently up to 20 stories) designed to AISC 360 and 341 (and 358 where appropriate): OpenSees analysis embedded in the session, ASCE 7 loads, all members and connections designed, lateral stability checked.

GitHub ↗ · Example report ↗ · Example 3D model ↗

// Example library

36 worked buildings

Every example brief that ships with Steltic, designed end to end by Claude Fable 5.

View report ↗ View 3D model ↗

// Cold-formed steel — AISI S100/S240/S400

Steltic CFS

Cold-formed steel buildings designed to AISI S100-16 (R2020) w/S2,S3, S240-20 and S400-20 with ASCE 7-22 loads: wall-path buildings (WSP, steel-sheet, strap-braced and gypsum shear walls, Type II segments, podium and mixed systems, up to 8 stories) and portal-frame buildings, with stud/track/chord, connection, anchorage and drift design in every package.

GitHub ↗ · Example report ↗ · Example 3D model ↗

// Example library

25 worked buildings

Every in-scope example brief that ships with Steltic CFS, designed end to end by Claude Fable 5.

View report ↗ View 3D model ↗

// Steltic Non Linear

Introducing Steltic Non Linear. It takes steel buildings designed by Steltic then undertakes: Pushover (ASCE 41-23 and AISC 342-22), NLRHA (eleven real earthquakes per ASCE 7-22 Chapter 16) and Direct Design Method analyses (a GMNIA fibre model with imperfections and residual stresses, every load combination scaled to collapse).

GitHub ↗ · Play with the four viewers ↓

Introducing Steltic Non Linear

// See it in action

Watch Steltic work

Initial design run — AISC (using Opus 4.8 Fast to reduce the video time)

Optimize, add figures and finalize — AISC

// Play with a real building

Four analyses, one model — live on this page

Ex22_SMF is the 6-story hospital SMF (Risk Category IV) that ships with Steltic Non Linear, shown exactly as the assistants deliver it: the Steltic design model, then the pushover, NLRHA and DDM runs on that design. Drag to orbit, scroll to zoom, and use the module strip to move between the four analyses.

Ex22_SMF

↗

Drag to orbit · scroll to zoom · R resets the view · the strip inside each viewer switches modules too. NLRHA and DDM are big models — the first click on those takes a moment to load. These viewers are built for a desktop screen — tap ⤢ for full screen.

// BUILD A STELTIC-GROK BOT

Four Grok Bots, two prompts each. Copy from the slider — full files on github.com/Steltic/steltic_grokbot.

Steltic-Grok Bot — steel design and specification querying all within your Grok Bot

Query file manager

Prompt 1

Load skills/Skill_query_file_manager_PACKAGED.md as a skill.

Prompt 2

Clone https://github.com/Steltic/steltic_grokbot onto your computer. Copy scripts/ to /workspace/engineering_rag/scripts and engineering_rag_phase2/ into /workspace/engineering_rag/. Create a Python venv at /workspace/engineering_rag/.venv, install Docling 2.123.1 (do not upgrade it without revalidation), and set TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata/ and DOCLING_DEVICE=cpu. Tell me when that bootstrap is done.

HR Steel App

Prompt 1

Load skills/Skill_querying_PACKAGED.md as a skill.

Prompt 2

Clone https://github.com/Steltic/steltic onto your computer. Install it per the README (Python 3.12, pip install -e . — openseespy needs native libs, install those too). Verify by running the app with model MOCK and confirming a design package appears. Then read contract/AGENT_START.md: for future design tasks you will follow that contract yourself — write cfg.py, run the engine via python in your terminal, fill the calc package, run consistency.check, and deliver report.html + viewer_3d.html. Let me know after you complete the MOCK tests, then Run the first example building end to end that way.

CFS Steel App

Prompt 1

Load skills/Skill_querying_PACKAGED.md as a skill.

Prompt 2

Clone https://github.com/Steltic/steltic_cfs onto your computer. Install it per the README (Python 3.12, pip install -e . — openseespy needs native libs, install those too). Verify by running the app with model MOCK and confirming a design package appears. Then read contract/AGENT_START.md and contract/CFS_REFERENCE.md: for future design tasks you will follow that contract yourself — write cfg.py, run the engine via python in your terminal, fill the calc package, run consistency.check, and deliver report.html + viewer_3d.html. Let me know after you complete the MOCK tests, then Run the first example building end to end that way.

Steltic Nonlinear

Prompt 1

Load two skills from https://github.com/Steltic/steltic_grokbot: skills/Skill_querying_PACKAGED.md and skills/Skill_SNL_PACKAGED.md.

Prompt 2

Clone https://github.com/Steltic/steltic_nonlinear onto your computer, next to the Steltic (HR) repository (the DDM step needs its steel_engine folder). Create a Python 3.12 venv (openseespy only ships wheels for 3.10–3.12) and pip install -e . in the repo — that installs pushover, nlrha, steltic_ddm, the snl orchestrator, openseespy, numpy, scipy and matplotlib; the P-695 ground-motion library ships in records/. Set STELTIC_ENGINE_DIR to the absolute path of steltic/steel_engine.

Verify the install on the packaged example, no retrieval needed:
  python -m snl inspect examples/Ex22_SMF
  python -m snl report  examples/Ex22_SMF
  python -m pytest tests -q
  python -m snl run examples/Ex22_SMF --only pushover --params examples/Ex22_SMF/hinge_params_ex22_aisc342.json

Open examples/Ex22_SMF/steltic_viewer_bundle.html and flip through the four viewers with the module strip.

From now on, for every job, follow skills/Skill_SNL_PACKAGED.md: python -m snl inspect <zip>; send ONE wave-1 retrieval plan to Query file manager (AISC_342_22, ASCE_41_23, ASCE7 Ch.16, AISC_341_22); fill the job copy of hinge_params.json from the excerpts and set verified=true only when every needed block is cited; run python -m snl run <zip> --params <job>_hinge_params.json --steltic-engine $STELTIC_ENGINE_DIR --parallel 2; judge pushover, NLRHA and DDM each with its own protocol; deliver the job folder (pushover/, nlrha/, ddm_*, steltic_viewer_bundle.html, four_analyses.html, snl_summary.json) with your four-analyses narrative, retrieval_log.md and open items. Product defaults: docs/PRODUCT_DEFAULTS.md.

Report back now: the example's Omega in X and Y, the BSE-2N target displacements, and confirm the viewer bundle opened.

// SINGLE PROMPT BUILD

If you want to add all Steltic assistants to your Grok Bot, create one bot called Admin (for example), then give it this single prompt:

Prompt A — paste into Admin

You are the site Admin for a new Steltic Grok Bot install. Create four teammate Grok Bots (use CreateAgent), then message each one its setup prompts so they bootstrap themselves. Do not design buildings yourself.

Create these bots (names exact):
1. Query file manager
2. HR Steel App
3. CFS Steel App
4. Steltic Nonlinear

Then SendToAgent each bot the messages below, in order 1→4. For each bot: first send Prompt 1, wait until they confirm the skill is loaded (or send both in one message clearly labeled Prompt 1 then Prompt 2). Report back when all four have been created and messaged.

=== Query file manager — Prompt 1 ===
Load skills/Skill_query_file_manager_PACKAGED.md from https://github.com/Steltic/steltic_grokbot as a skill.

=== Query file manager — Prompt 2 ===
Clone https://github.com/Steltic/steltic_grokbot onto your computer. Copy scripts/ to /workspace/engineering_rag/scripts and engineering_rag_phase2/ into /workspace/engineering_rag/. Create a Python venv at /workspace/engineering_rag/.venv, install Docling 2.123.1 (do not upgrade it without revalidation), and set TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata/ and DOCLING_DEVICE=cpu. Tell me when that bootstrap is done.

(After Prompt 2, remind the user: Supply the specs — place your own licensed PDFs in the working-folder standards/. Follow the first-run sequence in the Query file manager skill. The Bot will run retrieval checks on the converted specifications, revise as needed, then report when they are ready for design. Also convert ASCE/SEI 41-23 and ANSI/AISC 342-22 with stems ASCE_41_23 and AISC_342_22 for Steltic Nonlinear.)

=== HR Steel App — Prompt 1 ===
Load skills/Skill_querying_PACKAGED.md from https://github.com/Steltic/steltic_grokbot as a skill.

=== HR Steel App — Prompt 2 ===
Clone https://github.com/Steltic/steltic onto your computer. Install it per the README (Python 3.12, pip install -e . — openseespy needs native libs, install those too). Verify by running the app with model MOCK and confirming a design package appears. Then read contract/AGENT_START.md: for future design tasks you will follow that contract yourself — write cfg.py, run the engine via python in your terminal, fill the calc package, run consistency.check, and deliver report.html + viewer_3d.html. Let me know after you complete the MOCK tests, then Run the first example building end to end that way.

=== CFS Steel App — Prompt 1 ===
Load skills/Skill_querying_PACKAGED.md from https://github.com/Steltic/steltic_grokbot as a skill (same file as HR).

=== CFS Steel App — Prompt 2 ===
Clone https://github.com/Steltic/steltic_cfs onto your computer. Install it per the README (Python 3.12, pip install -e . — openseespy needs native libs, install those too). Verify by running the app with model MOCK and confirming a design package appears. Then read contract/AGENT_START.md and contract/CFS_REFERENCE.md: for future design tasks you will follow that contract yourself — write cfg.py, run the engine via python in your terminal, fill the calc package, run consistency.check, and deliver report.html + viewer_3d.html. Let me know after you complete the MOCK tests, then Run the first example building end to end that way.

=== Steltic Nonlinear — Prompt 1 ===
Load two skills from https://github.com/Steltic/steltic_grokbot: skills/Skill_querying_PACKAGED.md and skills/Skill_SNL_PACKAGED.md.

=== Steltic Nonlinear — Prompt 2 ===
Clone https://github.com/Steltic/steltic_nonlinear onto your computer, next to the Steltic (HR) repository (the DDM step needs its steel_engine folder). Create a Python 3.12 venv (openseespy only ships wheels for 3.10–3.12) and pip install -e . in the repo. Set STELTIC_ENGINE_DIR to the absolute path of steltic/steel_engine.

Verify the install on the packaged example (no retrieval needed):
  python -m snl inspect examples/Ex22_SMF
  python -m snl report  examples/Ex22_SMF
  python -m pytest tests -q
  python -m snl run examples/Ex22_SMF --only pushover --params examples/Ex22_SMF/hinge_params_ex22_aisc342.json

Open examples/Ex22_SMF/steltic_viewer_bundle.html and flip through the four viewers.

From now on, for every job, follow skills/Skill_SNL_PACKAGED.md: inspect the HR package zip; send ONE wave-1 retrieval plan to Query file manager; fill the job hinge_params.json from excerpts; run python -m snl run <zip> --params <job>_hinge_params.json --steltic-engine $STELTIC_ENGINE_DIR --parallel 2; judge pushover, NLRHA and DDM; deliver the job folder with four_analyses.html, steltic_viewer_bundle.html, narrative, retrieval_log.md and open items. Product defaults are in docs/PRODUCT_DEFAULTS.md (NLRHA ModIMK→PZ×1→fibre; dual-gate; CFS DDM Tier 2; HR DDM/NSP fibre+mesh 10%).

Report back: example Omega in X and Y, BSE-2N targets, viewer bundle confirmed.

// FAQ

More about Steltic

// About — What is Steltic?

Steltic is a family of free, open-source structural design assistants for engineers: an agentic harnessi that drives an AI LLM through the full steel design workflow — hot-rolled steel (AISC 360/341), cold-formed steel (AISI S100/S240/S400), and nonlinear checks on finished designs (pushover, NLRHA, DDM). The assistants live on GitHub.

Steltic has no LLM of its own — it is an LLM harness that guides your LLM through the structural design workflow but generates no engineering content of its own; every model, calculation, figure, and report is produced by your LLM. You simply input your API URL and API key at the beginning of your session (you pay the LLM costs).

The harness is designed to lead the LLM through a first pass, then enters a traditional "chat" format, wherein the building is now in context and the user can ask the LLM to make any changes.

Quick Start — 61 worked example buildings ship across the HR and CFS assistants (36 AISC + 25 CFS). Install locally and design your own, or run the shipped examples.

// LLMs — What LLM should I use?

Steltic has been internally tested thoroughly with Claude Fable 5 and ChatGPT 5.6 Sol. These frontier models perform exceptionally well and typically complete the full design with no human-in-the-loop. Notably, ChatGPT 5.6 Sol systematically designs quite conservatively in the initial no human-in-the-loop run (this simply requires the user to prompt an optimization run following the first completion). Limited testing has shown Opus 4.8 to also be very good. Without doubt, Fable 5 is the best choice for excellent results.

Open-weight models — Zai GLM 5.2 and DeepSeek 4 Pro have been extensively tested; however they perform substantially less well, sometimes forget the agent instructions, sometimes "spin their wheels" on unimportant issues, and generally require substantial human-in-the-loop support.

Other LLMs — any LLM for which a user has an API key can be used in the harness; however, as with all AI products, less intelligent models will give less intelligent results. Nonetheless, you can test any model you wish.

// Grounding — Don't LLMs hallucinate?

Your LLM is fully grounded to the latest specifications and design procedures. The AISC assistant has access to RAG vector databases of AISC 360, 341 and 358 (2022), an examples database of OpenSees models, two databases of the OpenSees documentation, and the AISC Steel Construction Manual Design Examples of 168 design examples (V16.0). The CFS assistant is grounded the same way to AISI S100-16 (R2020) w/S2,S3, S240-20 and S400-20. Steltic Nonlinear retrieves ASCE/SEI 41-23, ANSI/AISC 342-22, ASCE 7 Chapter 16 and related clauses through Query file manager. These corpora are built from your own licensed PDFs (or hosted privately when you run grounded servers), and Steltic directs your LLM to query them to ground its calculations.

// Inputs and Outputs — What goes in, what comes out

Running it yourself — input is anything you can describe. In the open-source versions you write the brief in text (stories, bays and spacings, loads, seismic, system), attach drawings or PDFs if your model reads images, and keep working with the agent afterwards. After the initial run your building is in context, so you can change the geometry, change the seismic LFRS, optimise the member sizes based on the drift, etc. Simply chat with your LLM to investigate any alternative designs.

Outputs. A structural engineering report (report.html) written to the level a senior engineer needs for review, the analysis model files, an interactive 3D viewer of that model, the conversation history and the reasoning trace where your model exposes one. The 3D viewer is how you verify the modelling. In the open-source versions you can modify the report parameters to include anything you think is useful for reviewing purposes. You get consistent data output for every building, every design, every time.

Browse the worked examples ↑