Using AI to Generate or Troubleshoot Artisan Bread Recipes—What’s Your Experience?

Toast

Hey fellow bread lovers,

I’ve been baking sourdough long enough to trust my hands... but lately curiosity got the better of me, and I asked an AI to help draft a bread recipe. It plopped out something that looked technically plausible—flour, water, starter, salt—plus, oddly, a comment that had me grinning: “If your loaf flattens on day two, blame the yeast, not the baker.”

It wasn’t perfect by any means—hydration was a bit off, timing felt tight—but it gave me a starting point I didn’t have to craft from scratch. Kind of neat, like having a sous-chef who knows code.

So I’m wondering:

Has anyone else tried using AI for baking recipes, whether with a full loaf or a tweak here and there?

Did it spark your creativity, inspire new ideas—or crash and burn spectacularly?

Curious to know if any of you let AI “draft” a recipe and then adapted it with your baker’s intuition?

Let’s share our funniest prompts, weirdest outcomes, or best AI-inspired tweaks. After all, even if the loaf isn’t perfect, the story behind it can be as delightfully crusty as a great sourdough.

— A baker who codes and codes while kneading 😄

I used it a couple of times to make recipes more diet restriction friendly. I plug in the recipe and then explain what changes I want to happen. It does a really good job giving me replacements and gives me fun new ingredients or methods to research. 

As I'm sure we are all aware at this point, AI is far from all knowing. It will often times spit out something that looks good on the surface, but when it comes down to it, the information is off a beat. It always best to use it as a learning reference rather than an absolute answer.

Hope your AI bread executes flawlessly, and you have a bug free day!

I do use chatbots - I refuse to call it "AI" - from time to time but I never ask for a bread recipe.  The only time I would do that is if I have a partly-remembered recipe and wanted to track down the source or the entire recipe.

Mostly I start a dialog, and it often works much like talking something over with a person in that new or remembered things come to mind.  Sometimes I learn something new that's useful. Sometimes I remember things I knew but hadn't thought of for a while or hadn't put together in quite this way.

Here's my initial question in a recent chat:

There is a recipe for rye bread that calls for leaving buttermilk out at room temperature then mixing it with rye flour and leaving it covered at room temperature for another 24 hours. This is an unusual schedule for making bread. What is the name of this kind of rye bread?

Later in the session I asked this:

This recipe came up on the fresh loaf site in connection with food safety. I wasn't sure what the pH would be after mixing in the rye flour, nor whether the pH could be expected to decrease much during the 24 hour subsequent fermentation. I know that a dough made with sourdough starter will have its pH decrease into the food-safe zone fairly quickly but wasn't sure if that would happen with the buttermilk-only dough.

A discussion about pH, buttermilk, and food safety followed.

Another recent start to a chat:

I plan to make sourdough bread including 15% (baker's percent) each of ground pistachios and ricotta. I plan to mix the dough without the additions first and later add the nut/cheese mixture. I don't know how much water the ground nuts will absorb so I don't know how much water to hold back during initial dough mixing. I do know that ricotta contains about 80% water. Guidance for estimating the water-absorbing ability of the ground pistachio powder?

Later the chatbot over-analyzed things and offered to come up with a detailed recipe and procedure.  But I had my own plan.

One more example of a recent chat:

There is a style of sandwich roll or bun that share common features: very light airy crumb, somewhat elastic crumb that won't squish down completely, very thin, crackly yet flexible crust. Varieties include names like hoagie, sheboygen, banh mi, etc. It's not easy to make these buns successfully with all the intended features. What are common best practices for making these buns at home?

This chat was interesting, with the chatbot pointing out differences between many of the common roll types.

I try to pose questions that should be commonly written about (in the training material), so as to get the best chance of correct or useful results.  The newest version of ChatGPT is more neutral to work with and I like that.  It also seems to be better at "understanding" the context and brings in a wider range of apparently relevant material.  I don't expect that arithmetic will come out reliably and I don't ask for that (even though the arithmetic seems to be getting better - I haven't tested it lately).

I have a standard prompt I usually include:

Your ground rules:
1. Do not praise my remarks or try to give positive or fawning feedback.
2. If you do not know something, or make assumptions, say so.
3. Do not restate my remarks before making your own responses.
 

TomP

Tom, those conditions are interesting.  My preferred chatbot calls itself an AI Assistant, so what are your objections to using "AI"?

 

Yes, I regularly use "them" for recipes, outlining the ingredients and/or quantities I want. No funny stories, but once it left out an important ingredient. Caught it before I used the recipe.

They can call themselves whatever they like, but for me what we have now is nowhere near a general artificial intelligence.  For me, to be intelligent they need to have problem-solving skills and be able to assess or evaluate the quality (and common-sensibleness) of their responses. Until then, the term "AI" is hype that I wish to avoid.  So I say "LLM" or "chatbot". Although I suppose I won't be able to avoid "AI" eventually.  

I gotta admit, though, that especially with the new model of ChatGPT, the responses are sounding surprisingly cogent and conversational.

One feature of these things that I find interesting is that they may "know" something, but they don't know where the information comes from.  I'm like that too.  If I ask the chatbot for a reference it will run an internet search, but it can do that much faster than I can.  Sometimes the references are good, sometimes they aren't very on-point.

I recently had a long session with Grok about English muffins, which resulted in three interesting recipe options. I am now making quite good English muffins, so you could say it was successful. I did have one failed batch initially, because I tried the most extreme option first. 

If you offer background input to the AI, like your baking specialties and experience, it can help tailor the response you receive. So for example, I am primarily a  panettone and shokupan baker, so Grok framed the English muffin conversation with that in mind. 

I did find that AI has some blind spots because of course it cannot really perceive organoleptically, so you must take its opinion with a grain of salt, so to speak. 

I have been using ChatGPT for a few months, and Claude more recently, mainly as an education tool where I want to drill deeper into the 'why' for certain techniques.  I have generally found it very helpful, but it requires an intense amount of reading and skepticism.  The more I use these tools, the more challenging I get to the bot to justify its answers and clarify what it is saying.  I now have a much better understanding of how sourdough starter works,  what the impact is of different feeding ratios and different flours.  Just this week it explained to me why using bread flour for a new starter was a bad idea, and why Rye flour performs the way it does in building a starter.  

In the early days of using it for bread recipes, i had an absolute fail with the recipe it came up with,  (92% hydration), and learned that I must always check its math.  No exceptions.  But on the flip side, it taught me to always hold water back in reserve when mixing dough, and learning what the 'feel' of a dough is, and what my own limit is on shaping high-hydration dough. 

OpenAI did a very good job recently of explaining the 'why' of steam in baking.  The reason we got on this topic was that I asked if there was any downside to simply opening a 550F pre-heated oven and spraying water with a pump sprayer into the oven box.  (turns out its not a great idea.  Likely void the warranty.)

Most entertaining - I did come up with my own recipe for a Thai curry ice cream.  

One more - it was bang on converting from instant yeast to a combination of sourdough discard/active dry yeast.  I was pleasantly surprised at the result.  I'm done with sourdough crackers, now I use my discard to make more bread.  

And kudos to @tpassin for the ground rules.  That is a true time saver.  

 

Those ground rules make for a real improvement, don't they?  Glad they were useful for you. I got an earlier version directly from ChatGPT by asking it to suggest ground rules for the kind of conversations I wanted to have (and what I didn't want included). Later I refined them to the form they have now.

What reason did the chatbot give for claiming that bread flour for a new starter is a bad idea?  Bread flour as opposed to All-purpose, bread flour as opposed to some whole grain flour, or something else?

TomP

from ChatGPT:

Why early-stage starters can struggle on bread flour only

1. Nutrient availability

  • Bread flour is basically just refined endosperm.
  • Compared to whole wheat or rye, it has far fewer minerals (like magnesium, iron, zinc), vitamins, and trace elements that microbes need to thrive.
  • Yeast and lactic acid bacteria (LAB) rely on these micronutrients to multiply and establish dominance in the early days.

2. Enzyme activity

  • Whole grains (esp. rye) are rich in amylases — enzymes that break down starch into simple sugars (maltose, glucose, etc.) that microbes can eat.
  • Refined bread flour has much lower enzyme activity. Early on, before the microbial population is strong, this can mean not enough food gets unlocked fast enough for the microbes to flourish.
  • That’s why rye is famously “turbo-charging” — it brings its own enzymatic toolbox.

3. Microbial diversity

  • The flour itself brings in microbial “seed stock.” Whole wheat and rye carry way more naturally occurring yeasts and bacteria on the bran/germ surfaces.
  • Bread flour is more sterile (bran/germ stripped away, roller-milled, sometimes bleached), so there’s a smaller microbial population entering the game.
  • With fewer players, the starter can take longer to stabilize or might stall before the right balance is achieved.

4. pH and buffering

  • Early on, acidification is crucial — LAB lower the pH to suppress unwanted microbes.
  • Whole grain flours buffer better (thanks to bran minerals and proteins), so LAB can thrive without the pH dropping too fast.
  • On pure bread flour, there’s less buffering capacity, which can let the environment swing in ways that inhibit the beneficial microbes.

In short:

  • Bread flour = “clean” but nutrient-poor → slow to kick off a microbial ecosystem.
  • Whole wheat/rye = nutrient- and enzyme-rich → fuels early microbial explosions, helps LAB/yeast establish quickly.

That’s why you’ll often see starter guides recommend rye or whole wheat for the first week, then transition to bread flour once the culture is stable.

That's interesting. I agree with some of the response but not all.  I just had my own little chat about this.  The use of the term "bread flour" is misleading.  It really means "any white refined (roller-milled) flour that might be used for making bread". The claim that rye flours are very high in yeasts isn't right.  Whole grain rye flours are especially rich in LABs but not in yeasts. Most of those organisms are found in the bran and you can just use the bran at the beginning. Later you will want to add flour for its starch

Most refined unbleached flours in the US contain diastatic malt or amylase, which will help bread down the starch in the flour so there will be an adequate supply of nutrition for the microbes. Quick acidification is desirable to suppress undesired organisms. A paste of water and bran that I tested held the pH above 6 for some time, which is the opposite of what you want, apparently because of the bran's buffering ability. BTW, water + bran alone starts out at a rather higher pH than water + flour.

What was effective in rapidly lowering the pH of the bran solution was to mix in some live-culture yogurt.

My experience, in agreement with the above, is that you can rapidly create a working starter using white refined, unbleached, malted flour and an acidifying agent. Pineapple juice and brine from salt-fermented pickles were very effective, and water plus live-culture yogurt should also work well.
OTOH, if the white flour has been bleached or isn't malted (or have amylase added) and even more so if you don't use an acidifying agent, then using bran or whole grain flour is undoubtedly going to be very helpful.

  • Whole grains (esp. rye) are rich in amylases — enzymes that break down starch into simple sugars (maltose, glucose, etc.) that microbes can eat.
  • Refined bread flour has much lower enzyme activity. Early on, before the microbial population is strong, this can mean not enough food gets unlocked fast enough for the microbes to flourish.
  • That’s why rye is famously “turbo-charging” — it brings its own enzymatic toolbox.

2. Is partially inaccurate / misleading and is an example of a particular weakness of AI, in that it doesn't have oversight and so bundles together facts viewed myopically.

Wholewheat is indeed richer in enzymes, however amylase activity as measured by the amylograph will demonstrate little difference between wholewheat flour and bread flour made from the same batch of grains. They will have more or less the same falling number.

Rye typically has higher amylase activity compared to wheat.

Amylase activity is related to the grain itself, growing conditions and how sound the wheat is. Milling to wholewheat or white (bread) flour has little bearing on starch conversion rate.

Wheat growers aim for high falling numbers for bread wheat and millers are unlikely to accept grains which give a falling number much below 300. However for the purposes of bread-making bakers prefer more amylase activity. In the US, additional amylase is often added to the flour while in Europe malt is added in the bakery.

@cbum63 - If you wanted some comedy for your research, this one is not bad.

I know this is a little long,  but the punchline is worth it.  It's an exchange with the Anthropic bot (Claude) on the definition of a 'levain'.  And if anyone here can enlighten me on what a levain really is, particularly after reading this exchange, I'm all eyes and ears. I know it just can't be that complicated.  

 

Me:

In this sourdough recipe, the author says : "This dough does not use a levain, but an active sourdough starter must be used." What's the difference between an active starter and a levain? I had always thought that any starter you fed the day before for baking, and had it measured out properly, was the levain.

Claude:

You're thinking of the more common usage! In many contexts, "levain" and "starter" are used interchangeably, and what you described - starter that's been fed and is ready to bake with - is often called a levain.

But this author is probably making a technical distinction. A "levain" typically refers to a portion of starter that's been built up specifically for a recipe - you take some of your mother starter, feed it at a specific ratio for that particular bread, maybe over multiple feedings to get the right amount and activity level.

When they say "active sourdough starter," they likely mean you're using your regular maintained starter directly - as long as it's active and bubbly from recent feeding. No special build-up or separate levain preparation.

It's honestly a bit of terminology splitting that varies between bakers and authors. Some use "levain" to mean any active starter used in bread, others reserve it specifically for that built-up portion. The practical difference here is probably just that you don't need to do any special starter preparation beyond making sure your regular starter is active and ready.

Kind of like how some recipes say "sourdough starter" and others say "levain" but mean essentially the same thing!

Me: 

But he says later on that the starter must be at or very near its peak. I'm curious why he added the levain comment, because he's implying that there's something different from an active starter at its peak, and a levain? I know i'm splitting hairs here, but even in some of the well-known bread books, they're pretty adamant about the difference. 

Claude:

You're absolutely right to dig into this - it's not splitting hairs, it's actually a meaningful distinction that serious bread bakers care about!

The difference is usually this: your "mother" starter is what you maintain daily/weekly - it's your ongoing culture. A levain (or barm, as Keller calls it) is typically a specific build from that mother starter, often with a particular flour blend, hydration level, or feeding schedule designed for that specific bread.

So you might take 20g of your mother starter and build it up to 200g with a specific ratio of flours over 8-12 hours to create a levain that's perfectly tuned for, say, a country loaf. Different from just using your regular active starter straight.

But this author seems to be saying "skip all that - just use your regular starter as long as it's at peak activity." Which is simpler but potentially less controlled.

The French books are adamant about it because they're often dealing with very specific flavor profiles and fermentation timings. A levain lets you control the exact characteristics of what's going into your dough, rather than whatever happens to be the state of your mother starter that day.

It sounds like this recipe author is going for simplicity over that level of control.

Me:

Now i'm really confused.

Claude:

Let me try to simplify this because it really is confusing terminology!

Think of it this way:

Mother starter = your ongoing culture you maintain (feed regularly, keep alive)

Levain/barm = a specific portion built from your mother starter for a particular recipe, often with specific ratios and timing

Active starter = your mother starter when it's bubbly and ready to use

So when this author says "no levain, just active starter," they're saying: "Don't do a special build-up process. Just use your regular maintained starter as long as it's active and at peak."

The confusion comes because many bakers (and recipes) use "levain" and "starter" interchangeably, but the purists make that distinction.

Your original understanding was actually correct for most practical purposes - if you fed your starter the day before and it's ready to bake with, that's what most people would call a levain. This author is just being more specific about technique.

Bottom line: use your regular starter at its peak activity. No special preparation needed.

Me:

Here's what i'm confused about. What might I be doing differently when building a levain or a barm? Is there a secret about feeding ratios i don't understand yet? I always thought i moved to 1:5:5 becuase i need to get to 140 grams in one go. There are nuances to what your starter is actually going to do to the dough?

Claude:

Ah, now I see where the confusion is! Yes, there are definitely nuances beyond just scaling up to get the right amount.

When building a levain, bakers might adjust:

Ratios: You might use 1:2:2 for a more acidic levain, or 1:10:10 for a milder one. Different ratios change fermentation speed and flavor development.

Flour types: Your mother starter might be 100% white flour, but you could build a levain with 50% whole wheat to add flavor complexity to that specific bread.

Hydration: Maybe your mother is 100% hydration, but you build an 80% hydration levain for a particular dough consistency.

Timing: You might build it to peak at exactly the right moment for your baking schedule, rather than whenever your mother happens to be ready.

Temperature: Building it cooler or warmer to control fermentation speed and flavor.

So your 1:5:5 ratio gets you to 140g, but a levain builder might think: "I want this bread to have more tang, so I'll do 1:2:2 and let it go longer" or "I want whole grain flavor, so I'll build with 30% rye flour."

It's about tailoring the starter's characteristics to the specific bread, not just scaling up for quantity. Your approach works great - this is just next-level tweaking for specific outcomes.

Me:

Ok, you cleared that up. But you've contradicted what you've already told me days ago, and that is this: For a healthy starter, I need to see the same results (predictability) for several feedings in a row. So if I'm feeding normally at 1:1:1, and i need volume, I need to plan to repeat that new hydration and volume for a few cycles. What i'm reading here is that I can monkey with the ratios on the last feed to get what I think i want. One of those concepts must be off.

Claude:

You're absolutely right to call that out - I did contradict myself, and your original understanding is correct.

For starter health and predictability, you DO need consistent feeding ratios over multiple cycles. You can't just suddenly jump to a completely different ratio on the final feed and expect predictable results.

What I should have said is: if bakers want those specific levain characteristics (different hydration, flour types, acidity levels), they typically establish that feeding pattern over several cycles before baking, not just on the last feed.

So if someone wants a 1:2:2 levain for more tang, they'd feed at that ratio for 2-3 cycles to let the starter adapt and become predictable at that ratio. Same with flour changes - you'd gradually introduce the new flour over multiple feedings.

The "monkey with ratios on the last feed" approach would give you unpredictable timing and potentially inconsistent results, which goes against everything about maintaining a healthy starter.

Thanks for catching that - your approach of maintaining consistency for predictability is the right foundation. Any ratio changes need to be established over multiple cycles, not just improvised at the end.

Me:

So then you can't build a levain the day before if you are moving the ratios around. And I thought that was the whole point of a levain - purpose built for tomorrow's bake.

Claude:

You've hit on the real contradiction in the terminology! This is exactly why it's so confusing.

You're right - if you need multiple cycles to establish new ratios, then you can't truly "build a levain the day before" with different characteristics. That would take several days.

I think what's happening is there are really two different things being called "levain":

  1. True levain building - changing ratios/flours over multiple cycles to develop specific characteristics (takes days)
  2. Scaling up for quantity - what you're doing with 1:5:5, where you're just making more of the same active starter for tomorrow's bake (one day)

Most home bakers (and many recipes) are really doing #2 but calling it a levain. The French traditionalists are talking about #1.

So when that bread author says "no levain, just active starter," they might be distinguishing between the multi-day process (#1) and just using your regular starter at peak activity.

Your 1:5:5 approach is really just scaling up your existing healthy starter - same characteristics, just more volume. Which is probably what most "levain" recipes actually want, despite the fancy terminology.

The whole thing is honestly muddled by inconsistent terminology across different baking traditions.

Me:

Are you saying that you are confused as well?

Claude:

Yes, honestly I am! This is one of those topics where the terminology has gotten muddled across different baking traditions, and I've clearly given you some contradictory information trying to reconcile different uses of the same words.

The sourdough world uses "starter," "levain," "barm," and "mother" in overlapping and sometimes conflicting ways depending on whether you're reading American home baking books, French technique manuals, or individual baker's interpretations.

I should have been clearer from the start that this terminology isn't standardized, rather than trying to give you definitive answers that ended up contradicting each other. Your confusion is totally justified - I was trying to explain distinctions that aren't actually consistently applied across the baking world.

Your practical approach (consistent ratios for predictability, scaling up when you need more) is solid regardless of what anyone calls it.