---
title: Iterate on favorites | FLORA API
description: Use prior outputs as inputs to explore variations of the ones you like.
---

After generating a grid, the most natural next move is *“more like #4 and #7.”* FLORA MCP makes this trivial: the outputs of one tool call become the inputs of the next, all in the same chat.

This is FLORA’s differentiator. Most generative MCPs are single-shot — they generate, then forget. FLORA Techniques accept image references as inputs, so context carries forward across calls.

**Prerequisite:** You’ve already run a Technique and have outputs in the conversation. Start with [Discover and run](/mcp/recipes/discover-and-run/index.md) if not.

## What you type

> Love #4 and #7. Can you make 5 more variations of those? Same visual direction, but explore composition and copy.

## What the agent does

1. Resolves your references

   The agent knows #4 and #7 are specific outputs from the previous run. It pulls their URLs from the chat context.

2. create\_technique\_run with image references

   The agent calls the same Technique again, this time passing #4 and #7 as `image_reference` inputs (or whichever input name your Technique uses for visual anchors). It sets `count: 5` and adds prompts like “explore composition and copy”.

3. Renders new grid inline

   A new grid appears, anchored to the visual direction of #4 and #7 but exploring the requested variation axis.

## What you see

> Locking in the visual direction from #4 and #7, exploring composition and copy.
>
> \[5 new thumbnails render progressively]

The original 3×3 grid is still in scroll. You can compare side by side without leaving the chat.

## Variations to try

- *“Make 10 more like #2, but pushing harder on the brand “warm minimalism” direction.”*
- *“Use #1 as the layout reference and #5 as the color reference. Generate 6 combinations.”*
- *“Try #4 again but with the headline from the brief instead of placeholder copy.”*

The more specific the directive, the better. The Technique decides which input slots accept image references vs text — the agent figures it out from `retrieve_technique` schema.

## Under the hood

```
# From the previous run, the agent knows:
#4 = https://ik.imagekit.io/flora/run_abc.../output_3.png
#7 = https://ik.imagekit.io/flora/run_abc.../output_6.png


create_technique_run(
  slug="thumbnail-v3",
  inputs={
    "brief": "...original brief...",
    "image_references": ["<url for #4>", "<url for #7>"],
    "directive": "explore composition and copy"
  },
  count=5
)
```

## Tips

- Output URLs are long-lived but not permanent. Re-running a same chat days later may fail if URLs expire — re-generate the favorites or [upload them as assets](/mcp/tools/index.md) first.
- If results drift too far from your favorites, increase the weight the agent assigns to references: *“Hold the visual direction of #4 even tighter — same lighting, same composition style.”*
- This pattern composes with Techniques that don’t natively accept references: the agent can describe the favorites in text and pass that description as the prompt.