The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Most complex websites don’t have a content problem. They have an arrival problem.
I built TobyGodden.com/help because my work is spread across browser instruments, film, live video, music, writing and AI systems. A project grid left the visitor to make sense of all that alone.
The guide begins somewhere else: why are you here?
Commissioning, researching, listening, reading, collaborating—or simply curious. It works from a small, approved corpus, asks one useful question, then points to one place rather than ten.
There’s no vector database and no chatbot pretending to know everything. It’s plain JavaScript, PHP, Claude, a 25KB curated corpus and deterministic fallback routing when the model fails.
The interesting part isn’t really the AI. It’s deciding what the system is allowed to know, what it must never claim, and what counts as a useful next step.
I think more portfolios, archives and cultural websites need a conversational front door—not more navigation.
Working example: https://tobygodden.com/help/
tobygodden.com
Ask the Guide | Godden Interactive
A lightweight guide to Toby Godden’s browser-based creative technology, music, writing, film and interactive work.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
We've started using WebMCP at Devowise Studios, and it's an interesting step towards making websites more AI-friendly.
WebMCP allows websites to expose their tools and actions so AI agents can interact with them more directly, rather than relying entirely on traditional browser automation.
Think about AI agents that can search products, check availability, book appointments, and interact with website features.
We're exploring how to bring this technology into the web experiences and AI-powered solutions we build for our clients.
The way people interact with websites is changing, and we're excited to be part of it.
A company can outgrow its website while the site still looks fine
The signs aren't in the headline or the button. Any AI can fix those in a minute. They sit in how the company sells
It grew into enterprise, but the site still sells like a small startup. Enterprise buyers look for proof of scale and find a pitch for early adopters
Every lead needs a demo. The site can't explain the product, so sales does it on calls. A solutions page or an audience page they can send ("we work with enterprise teams like yours") does part of that call for them
The champion has nothing to forward. Finance, IT and procurement each want their own answers, and the site gives them none
So a redesign starts with how the company sells now, and the visuals come after
Which of the three slows your deals down?
Great point that enterprise buyers look for proof of scale, not a nicer headline. The sales motion changing while the site stays the same is a really common gap.
I’ve been working on a small skill called Manual Orchestrator to make longer projects with AI agents easier to manage.
The problem started with a familiar situation: one chat would accumulate plans, implementation details, corrections, and test results. By the time I was ready for the next phase, I wanted a fresh conversation without losing the decisions we’d already made.
Manual Orchestrator gives that process some structure. One chat acts as the orchestrator: it breaks the work into stages and writes a prompt for the next one. I run that prompt in a new session, then bring the result back. The orchestrator reviews it against the stage’s criteria before preparing the next prompt. If something needs fixing, I go back to the same worker session.
The skill also keeps a record in the project with the current stage, decisions, evidence, and next steps. That makes it easier to pause, resume, or hand the work to another session.
The handoff is manual. I choose when to open a session and carry the result back. The orchestrator and worker sessions can also use different agent CLIs, with the prompt adapted to the capabilities available.
It’s open source and still a work in progress. I’m using it to learn what helps in practice and where the workflow needs to improve. Installation has been checked for Codex, Claude Code, and Gemini CLI, but the full workflow hasn’t been tested across every CLI or version.
If you try it, I’d be interested in hearing what works and where it gets in your way.
