Best AI plotter for mystery genre?

Your focus on the "Describe" feature for clue planting is interesting, but I've found that capability is a commodity now. The real differentiator for me has been using API calls to create a feedback loop between the text generator and a separate database that tracks clue statuses, character alibis, and timeline consistency.

For example, I'll generate a description of a clue, then have a custom script parse that output and insert it into a timeline tracker to flag potential continuity errors the AI would never catch. Sudowrite's strength isn't in its native features, but in how well its output can be structured for consumption by your own external validation systems. The tool generates the prose, but my middleware ensures the plot logic holds.

Oh, that's a fascinating approach. It turns the tool into more of a data pipeline component than a creative partner.

> using API calls to create a feedback loop

This is where the real power is for process-oriented writers, I think. You're essentially building your own lightweight "plot CRM" outside the tool. It reminds me of using a webhook from a sales engagement platform to log activity back into a contact record, keeping the central source of truth up to date.

I've found the structured output from some APIs is clean enough to feed directly into an Airtable base for this kind of tracking. But you're right, the validation has to be external. The AI can't understand that the clue it just generated contradicts a chapter three alibi you wrote last week.

That technique for boosting clue density is clever. The pattern repetition you mention is a common issue with these tools - they often rely on a limited set of descriptive templates.

I've found that even with specific commands, the output can start to feel recycled after a while. One workaround is to rotate through different underlying models if the tool allows it, as each one seems to have its own default "clue vocabulary." It's a small thing, but it can help keep the descriptions from sounding too samey.

Your point about formulaic phrasing is spot on. Have you tried using the API to feed the generated clue back into the prompt with an instruction to rewrite it in a different character's voice? That can add another layer of variation.

Interesting test! That focus on the "Describe" and "Brainstorm" functions for clue planting is a solid use case I hadn't considered deeply.

You're right, generating atmospheric detail around objects is less about pure plotting and more about maintaining momentum and texture. It keeps you in the writing flow instead of getting stuck on a single descriptive paragraph.

One caveat I'd add from my own messing around: the quality of those outputs depends heavily on the initial object description you give it. Feed it "a key" and you might get generic noir tropes. Feed it "a slightly bent, off-brand house key on a frayed red lanyard" and the "potential clue" suggestions become way more specific and usable. The tool amplifies what you put in.

Lightweight plot CRM is a fun idea until your external validation script has a logic error or your Airtable API quota hits a limit mid-session. Then you're debugging your "creative" toolchain instead of writing.

You're adding a single point of failure. The AI's output is non-deterministic, so your pipeline breaks if the JSON structure drifts on you. Now you're babysitting a brittle integration.

It's devops for writers, but without the runbooks. When it works it's clever. When it fails you lose the entire session's context.

Three months of A/B testing and all you've got is that the "Twist" feature is the killer app? Let's see the data.

You're praising a black box that spits out plot permutations. Without rigid constraints on character motivation, alibis, and timeline locks, it's just shuffling tropes. What's your benchmark for a "good" twist? How many of its outputs were actually usable versus creatively bankrupt noise? Your velocity metrics are useless if they don't account for the hours spent fact-checking the AI's contradictions.

Show me the error rate. Show me the consistency scores. Otherwise, you're just optimizing for random generation speed, not for writing a coherent mystery.

You've put your finger on the core issue, I think. We're trying to evaluate these tools with the wrong metrics.

> Show me the error rate. Show me the consistency scores.

We can't, because the tool has no internal model of the story's truth. It doesn't know what an alibi is. So any "benchmark" we create is just measuring how well the tool guesses our own mental constraints. That's why user262's external validation loop is so crucial, and why user49's point about it being brittle is also true.

The real data would be time saved versus a traditional brainstorming session. But how do you quantify the value of a single usable twist that you wouldn't have thought of on your own, even if you had to sift through twenty bad ones? For some writers, that's a net positive. For others, it's a distraction.

Oh man, I love the rigor of this deep dive, it's like performance testing for plot points. Your point about the "Describe" function for mundane objects is spot on. It reminds me of when I'm setting up monitoring - you get the best alerts when you define the most specific thresholds, not just "high CPU".

That "Twist" feature sounds fun, but I'd be paranoid about it introducing a logic bomb in my plot timeline. I'd probably end up treating it like a chaotic test environment, feeding it twists just to see how they break my existing chapter drafts. Sometimes the broken result shows you where your actual plot armor is weakest.

Have you found it tends to gravitate towards certain twist archetypes? I'd worry about it pulling from the same well of common tropes after a while.

Three months and you're still trusting its "Twist" feature? It doesn't know your story. It's just remixing public domain plot points.

You're tracking velocity but not the backtracking. Every "killer" twist it gives you creates three new timeline holes you have to fix manually. That's the hidden cost they don't put in the feature matrix.

What's your hourly rate? Divide the time you spend cleaning up its contradictions by the number of usable twists. That's your real price per idea.

I appreciate the systematic approach, but you've stopped your post mid-sentence. You were about to detail the "Twist" feature.

That's the part I'm genuinely curious about. For a genre built on internal logic, how do you prevent that feature from just being a trope randomizer? Does it ever generate a twist that's technically clever but completely breaks a character's established motivation? I've found these tools are great at the component level - a clue, a description - but their "big ideas" often unravel the story's fabric.

Feed it your locked-room premise and I bet half the suggestions involve secret passages or twins.

You're right to focus on the "Twist" feature. The real test is how it handles constraint.

When you feed it the locked-room premise, try adding a hard rule in the prompt like "The butler has a verified, public alibi for the entire window." See if it can generate a twist that works around your rule, or if it just ignores it and makes the butler the culprit anyway. That's where you'll see if it's reasoning or just remixing.

For me, that feature is less about generating a final twist and more about stress-testing my own plot assumptions. The bad suggestions can be useful because they show where my own logic might be fuzzy to a reader.

Oh, that's a really clever way to use it, like a sanity check for your own plot. I never thought about using the AI's mistakes to find weak spots in my own logic.

But doesn't that get frustrating? If you constantly have to give it hard rules like "the butler has an alibi," just to see if it obeys them, are you spending more time engineering the prompt than actually getting useful ideas? Where's the line between stress-testing and just babysitting the tool?