Q: What kinds of formulation questions can it answer?

Anything from “what ingredient base would work for an ambient plant-based protein shake at 20g per serving” to “what emulsifier options exist for an acidic beverage below pH 4.2.” It anchors every recommendation to real named products already on shelf, so you’re not getting theoretical suggestions. It’ll show you the ingredient list from Oatly’s protein line or Huel’s RTD, then suggest a formulation direction grounded in what actually works at scale. It also flags key challenges: if pea protein creates haze above 5% concentration and your concept needs clarity, it’ll tell you that before your R&D team discovers it in the lab. We call these “formulation directions” rather than “formulations” because they’re designed to give your food scientists a head start, not replace the lab work.

Q: How does the Food Science Agent work alongside our existing food scientists?

It handles the desk research so they don’t have to. When your food scientist gets a brief for a new plant-based RTD, they currently spend days pulling competitor ingredient lists, checking regulatory status across target markets, reviewing literature on stability and shelf life, and identifying possible formulation paths. The agent does that in minutes. Your scientists then review the formulation direction, apply their judgement and experience, and take the concept into the lab. We deliberately frame every output as a “formulation direction” with a clear note that lab validation is required. The goal is to compress the time from concept to informed R&D brief from weeks to hours, so your scientists spend more time on the high-value work: actual formulation, sensory testing, and scale-up.

Question 1

What exactly does the Food Science Agent do?

Accepted Answer

It gives your innovation and R&D teams instant, sourced answers to the food science questions that normally take days of desk research. Think of it as a specialist research assistant that can pull from USDA nutritional data, 2 million+ real product formulations on Open Food Facts, 225K flavour molecules from FlavorDB, published scientific evidence from PubMed, and regulatory databases from the EU, US, and UK. It does six things: builds formulation directions for new product concepts, finds molecular flavour pairings, identifies ingredient alternatives with trade-offs, checks regulatory status across jurisdictions, benchmarks competitor formulations, and finds cheaper ingredient options with relative pricing. Every answer cites its source with a direct link.

Question 2

What kinds of formulation questions can it answer?

Accepted Answer

Anything from &#8220;what ingredient base would work for an ambient plant-based protein shake at 20g per serving&#8221; to &#8220;what emulsifier options exist for an acidic beverage below pH 4.2.&#8221; It anchors every recommendation to real named products already on shelf, so you&#8217;re not getting theoretical suggestions. It&#8217;ll show you the ingredient list from Oatly&#8217;s protein line or Huel&#8217;s RTD, then suggest a formulation direction grounded in what actually works at scale. It also flags key challenges: if pea protein creates haze above 5% concentration and your concept needs clarity, it&#8217;ll tell you that before your R&#038;D team discovers it in the lab. We call these &#8220;formulation directions&#8221; rather than &#8220;formulations&#8221; because they&#8217;re designed to give your food scientists a head start, not replace the lab work.

Question 3

How does it handle regulatory considerations across markets?

Accepted Answer

It checks structured databases from the EU (food additives, flavourings, health claims, novel foods), the US (FDA GRAS status), and the UK (FSA post-Brexit data). When you ask &#8220;can I use ashwagandha in a functional beverage for the EU and UK market,&#8221; it checks the Novel Food Catalogue for EU authorisation status, the FSA for UK-specific divergence, and returns the exact authorised health claim wording you can legally put on the label, with conditions of use. It also runs a horizon scan via EFSA opinions and FDA Federal Register to flag upcoming regulatory changes that could affect your formulation. For markets without structured databases (Japan, Australia, GCC, etc.), it&#8217;s transparent about the gap: it shows you what it knows from EU/US/UK, then searches for the specific market&#8217;s requirements and flags that web-sourced data needs verification with a local regulatory consultant.

Question 4

Does it have depth in coffee and specialty ingredients?

Accepted Answer

Yes. The FooDB database behind the agent contains 70,000+ food compounds with health effects and food source mapping, which gives it strong coverage across specialty categories including coffee, functional botanicals, adaptogens, and novel proteins. For coffee specifically, it can pull compound-level data on chlorogenic acids, caffeoylquinic acids, trigonelline and other bioactives. That said, it&#8217;s most powerful when combined with your own internal ingredient knowledge. The platform is designed so that your company&#8217;s approved ingredients, supplier relationships, and proprietary formulations sit alongside the public databases, making the agent smarter about what&#8217;s actually available to you.

Question 5

How does the Food Science Agent work alongside our existing food scientists?

Accepted Answer

It handles the desk research so they don&#8217;t have to. When your food scientist gets a brief for a new plant-based RTD, they currently spend days pulling competitor ingredient lists, checking regulatory status across target markets, reviewing literature on stability and shelf life, and identifying possible formulation paths. The agent does that in minutes. Your scientists then review the formulation direction, apply their judgement and experience, and take the concept into the lab. We deliberately frame every output as a &#8220;formulation direction&#8221; with a clear note that lab validation is required. The goal is to compress the time from concept to informed R&D brief from weeks to hours, so your scientists spend more time on the high-value work: actual formulation, sensory testing, and scale-up.

Question 6

Can it work within our specific production constraints?

Accepted Answer

Yes. When you set up a project in The BOX, you define your constraints: production lines, existing equipment, certifications (organic, kosher, halal, BRC), target markets, margin requirements, allergen restrictions, and existing supplier relationships. The Food Science Agent uses these when generating recommendations. So if you ask for ingredient alternatives to acacia gum, and your company has a &#8220;no new vendor onboarding&#8221; constraint with Kerry Group as an existing supplier, the agent will flag which alternatives are available from Kerry and which would require a new supplier. It marks every recommendation as compatible, partially compatible, or blocked by a specific constraint, so you can see immediately what fits your reality.

Question 7

How current is the Food Science Agent's knowledge?

Accepted Answer

The structured regulatory databases (EU additives, EFSA health claims, FDA GRAS, UK FSA, Novel Foods) are refreshed monthly from the official EU DG SANTE API and other government sources. Open Food Facts updates continuously as products are added globally. FlavorDB and FooDB are research databases that update periodically. For anything fast-moving — a recent EFSA opinion on a food additive re-evaluation or a new US state-level ingredient ban — the agent searches live sources (EFSA, FDA Federal Register, Food Navigator) and flags the recency and confidence level of what it finds. You&#8217;ll always see whether an answer comes from a structured official database (high confidence) or a live web search (medium confidence, verify independently).

Your next product should be born from your constraints. Not killed by them.

Budgets are up. Processes haven't caught up.

AI-powered R&D, NPD, and product strategy, built around your reality

🎯

Constraints-first ideation

🧪

Food Science Agent

⚡

Brief to validated concept in weeks

📈

Product strategy intelligence

💬

Digital twins for concept testing

Real challenges from innovation, R&D, and NPD leaders

Questions from R&D, NPD, and innovation teams

See your next product in weeks, not months.