AWS Builder Center
Weekend Creative Agent Challenge: AstroMuse

Weekend Creative Agent Challenge: AstroMuse

What happens when an AI starship captain wakes up every day to look at the real universe? Learn how to build an always-on, memory-driven creative agent entirely on the AWS Free Tier.

LEAD AI Who has more than Decade year of experience in AI



Vision and what it does

The best tool is the one you never have to open. That line from the challenge brief became the whole design constraint for AstroMuse.
Space data is genuinely thrilling and almost always presented as though it isn't. NASA publishes an Astronomy Picture of the Day every single morning — a real photograph of a real object, with a paragraph of real astrophysics attached — and for most people it lands as another unread tab. Meanwhile every creative AI app I have built has the same flaw: it sits there, inert, waiting for a human to press Generate. The moment you stop pressing, the app is dead.
AstroMuse is my attempt to remove the button entirely. Every morning at 12:00 UTC it wakes up on its own, fetches today's real APOD, looks at the photograph with a vision model, and writes a three-paragraph starship captain's log grounded in what it actually saw and in the real astrophysics NASA supplied. It draws itself a retro 1970s pulp magazine cover, publishes the whole thing as a web page, and goes back to sleep. Nobody asks it to. There is no UI. You just open the page with your coffee and yesterday's universe has already been turned into fiction.
The part I care about most is the memory. Before writing, the agent reads its own last three entries back out of S3 and pulls forward a one-line note describing each entry's stylistic quirk, with an instruction to let the voice drift a little further today. So the captain is not a fresh stateless prompt every morning — the voice compounds. Over a week the logs get noticeably more clipped and stranger. The agent is not just always on; it is slowly becoming someone.

How I built it

The first decision was made for me. I planned to use Amazon Nova Canvas for the artwork, and my first  InvokeModel  call came back with  ResourceNotFoundException: This Model is marked by provider as Legacy . Titan Image Generator was not in the account's model list at all, and the Stability text-to-image models in  us-west-2  returned an  AccessDeniedException  for missing  aws-marketplace:Subscribe  permissions. Ten minutes in, my image pillar was gone.
Rather than spend the weekend chasing model access, I inverted the problem. NASA already supplies a genuinely spectacular image every day — I did not need to generate one, I needed to understand one. So Nova Lite reads the actual APOD photograph as a multimodal input and describes its shapes, colours and mood, and that description becomes grounding for Nova Micro's log. For the retro cover, I asked Nova Micro to emit raw SVG. Code as art. It turns out a small, cheap text model is a perfectly decent poster designer if you constrain it to a fixed  viewBox  and a whitelist of shape elements.
Two things bit me and both were about trusting model output too much.
First, I asked Nova Micro to reply in JSON and it dropped a comma between two keys.  json.loads  threw, my fallback fired, and the site published a raw JSON blob as prose. I replaced JSON with a plain labelled block —  STARDATE: ,  TITLE: ,  VOICE: ,  LOG:  — parsed with one regex. Small models drop punctuation constantly but almost never mangle a line-leading ALLCAPS label. That single change took the format failure rate to zero.
Second, and more seriously: I was about to embed model-authored SVG directly into my HTML. An LLM writing markup that lands unescaped on a public page is a stored XSS vector with extra steps. The fix was two layers. The SVG is written to its own object and embedded with  \<img src="..."\> , which stops browsers executing script inside it, and  sanitize_svg()  rejects any output containing  \<script\> ,  \<foreignObject\> ,  \<use\> ,  javascript:  or an  on*=  attribute, falling back to a hand-written cover instead. Every model and API string reaching the page goes through  html.escape() . There is a small assert-based self-check that fires if any of that regresses.
I also skipped SAM and CDK. The whole stack deploys from one idempotent  deploy.py  using boto3 — no Docker, no CloudFormation stack to debug at 2am. The Lambda uses only  urllib  and  boto3 , so there are zero dependencies to package.

AWS services used and architecture overview

EventBridge cron(0 12 * * ? *)
|
v
Lambda (Python 3.13, 512 MB, 180 s)
|-- NASA APOD API .................. today's real image + facts
|-- Bedrock: amazon.nova-lite-v1:0 .. vision, looks at the photo
|-- S3 GET logs/ ................... reads its own last 3 entries (memory)
|-- Bedrock: amazon.nova-micro-v1:0 . writes the log, then draws the SVG cover
v
S3 static website
index.html | archive/\<date\>.html | covers/\<date\>.svg (public)
logs/\<date\>.json (private)
  • Amazon EventBridge — the only trigger. One daily cron rule.
  • AWS Lambda — the whole agent, one file, no layers, no dependencies.
  • Amazon Bedrock — Nova Lite for vision, Nova Micro for prose and SVG.
  • Amazon S3 — static website hosting and the agent's memory store.
  • AWS IAM — a scoped role:  bedrock:InvokeModel  on exactly two model ARNs, S3 on exactly one bucket. No  FullAccess  anywhere.
The bucket policy is worth a note. Only  index.html ,  archive/*  and  covers/*  are public. The  logs/  prefix — the agent's memory — is readable by the Lambda role and nobody else, and I verified that with a  403  from the public URL.

What I learned

Model availability is a design input, not a detail. I assumed the image models in every tutorial would be there. Half of them were legacy-blocked or behind Marketplace permissions my IAM user did not have. Ten minutes of  list-foundation-models  and a throwaway  invoke_model  up front would have saved me an architecture. Now I check before I design.
The constraint made it better. A generated spaceship picture is what everyone else has. A model that looks at the actual telescope photograph and writes about what it sees is a different, more honest thing — and giving the SVG job to a text model produced a weirder, more charming cover than a diffusion model would have.
Structured output from small models wants structure, not JSON. Labelled lines beat JSON schemas when the model is cheap.
Statelessness is what makes agents feel fake. Adding one  list_objects_v2  and three  get_object  calls — maybe fifteen lines — is the difference between a cron job that generates text and something that reads like it has been out there a while.
Total cost: pennies a month. Nova Micro is roughly $0.000035 per 1K input tokens, the Lambda runs for about 20 seconds a day, and S3 holds a few kilobytes. It will run unattended for a year on the Free Tier.
Any opinions in this article are those of the individual author and may not reflect the opinions of AWS.
Enjoyed reading this content? Let the author know!

Your likes, comments, shares, and saves help creators reach more builders.

Loading recommendations

Loading article